Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog/Podcast
NEW
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/Podcast
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Initial Gemma-2B SAEs
Gemma-2B
Residual Stream
10-RES-JB
768
Prev
Next
MODEL
10-res-jb
Source/SAE
INDEX
Go
Explanations
mentions of the name "Sane" or variations thereof
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Configuration
jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
chanind/openwebtext-gemma
Features
16,384
Data Type
float32
Hook Name
blocks.10.hook_resid_post
Hook Layer
10
Architecture
standard
Context Size
1,024
Dataset
ctigges/openwebtext-gemma-1024-cl
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2b/10-res-jb/768?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2b/10-res-jb/768?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
596
+0.17
1.0%
50
+0.16
1.0%
1562
+0.15
1.0%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1562
+0.17
0.02
596
+0.16
0.02
1624
+0.15
0.02
Negative Logits
<bos>
-2.06
<?
-0.73
-0.71
ⓧ
-0.66
maging
-0.64
/*
-0.63
/**
-0.63
liel
-0.61
būs
-0.60
bawat
-0.59
POSITIVE LOGITS
Sa
1.49
Sa
1.38
sa
1.11
maer
1.05
Sá
1.04
sa
1.00
aen
0.98
glau
0.97
Sae
0.97
Saar
0.96
Act
ivations
Density 0.069%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
