Instructions to use google/gemma-scope-9b-pt-res with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- SAELens
How to use google/gemma-scope-9b-pt-res with SAELens:
# pip install sae-lens from sae_lens import SAE sae, cfg_dict, sparsity = SAE.from_pretrained( release = "RELEASE_ID", # e.g., "gpt2-small-res-jb". See other options in https://github.com/jbloomAus/SAELens/blob/main/sae_lens/pretrained_saes.yaml sae_id = "SAE_ID", # e.g., "blocks.8.hook_resid_pre". Won't always be a hook point ) - Notebooks
- Google Colab
- Kaggle
Download layer_30/width_16k/average_l0_226/hparams.json from google/gemma-scope-9b-pt-res: direct link, hf CLI and curl.
- Browser
- Download file 29 Bytes
-
https://huggingface.co/google/gemma-scope-9b-pt-res/resolve/main/layer_30/width_16k/average_l0_226/hparams.json
- Command line
-
hf download hf://google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_226/hparams.json
-
curl -L -o hparams.json https://huggingface.co/google/gemma-scope-9b-pt-res/resolve/main/layer_30/width_16k/average_l0_226/hparams.json
29 Bytes
| {"sparsity_lambda": 0.000125} |