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
Upload folder using huggingface_hub
Browse files
layer_0/width_131k/average_l0_21/params.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b64c23d1206150bf01355879e5cc7caa57ed90612762b4a3ea8f78e64325bf7
|
| 3 |
+
size 3759160648
|
layer_0/width_131k/average_l0_30/params.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc8aa871edd04108aabda4a6b7454bbf77a51e3de829a3a6f163f2718f756553
|
| 3 |
+
size 3759160648
|
layer_0/width_131k/average_l0_8/params.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad30db4b32226f7435ac348e2207af81eff48df90ddc0f7e77acdf1c6a1c6d19
|
| 3 |
+
size 3759160648
|
layer_0/width_16k/average_l0_129/params.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df0e10bd284a777d6cff3d218fefda6b8412e2d7e4764805dc21d5a7e3c32036
|
| 3 |
+
size 469908696
|
layer_0/width_16k/average_l0_35/params.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48a8f0785b893b03c043fa320b24601aee5e8391867fafdb43a83bdf7512582f
|
| 3 |
+
size 469908696
|