|
--- |
|
license: cc-by-4.0 |
|
library_name: saelens |
|
--- |
|
|
|
# 1. Gemma Scope |
|
|
|
Gemma Scope is a comprehensive, open suite of Sparse Autoencoders for Gemma 2 9B and 2B. Sparse Autoencoders are a "microscope" of sorts that can help us break down a model’s internal activations into the underlying concepts, just as biologists use microscopes to study the individual cells of plants and animals. |
|
|
|
See our [landing page](https://huggingface.co/google/gemma-scope) for details on the whole suite. This is a specific set of SAEs: |
|
|
|
# 2. What Is `gemma-scope-2b-pt-mlp`? |
|
|
|
- `gemma-scope-`: See 1. |
|
- `2b-pt-`: These SAEs were trained on Gemma v2 2B base model. |
|
- `mlp`: These SAEs were trained on the MLP sublayer outputs. |
|
|
|
# 3. How can I use these SAEs straight away? |
|
|
|
```python |
|
from sae_lens import SAE # pip install sae-lens |
|
|
|
sae, cfg_dict, sparsity = SAE.from_pretrained( |
|
release = "gemma-scope-2b-pt-mlp-canonical", |
|
sae_id = "layer_0/width_16k/canonical", |
|
) |
|
``` |
|
|
|
This uses **canonical** SAEs, those with average L0 closest to 100, which we expect to be reasonably useful for most tasks. The exact defined here is determined by this file in the SAELens repo, snappshotted on 22nd October 2024: https://github.com/jbloomAus/SAELens/blob/a470460/sae_lens/pretrained_saes.yaml#L2635 |
|
|
|
See https://github.com/jbloomAus/SAELens for details on this library. |
|
|
|
# 4. Point of Contact |
|
|
|
Point of contact: Arthur Conmy |
|
|
|
Contact by email: |
|
|
|
```python |
|
''.join(list('moc.elgoog@ymnoc')[::-1]) |
|
``` |
|
|
|
HuggingFace account: |
|
https://huggingface.co/ArthurConmyGDM |
|
|
|
# 5. Citation |
|
|
|
Paper: https://arxiv.org/abs/2408.05147 |
|
|
|
|
