Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Initial Gemma-2B-IT SAEs
Gemma-2B-IT
Residual Stream
12-RES-JB
8409
Prev
Next
MODEL
12-res-jb
Source/SAE
INDEX
Go
Explanations
references to a boy or boys
oai_token-act-pair · gpt-3.5-turbo
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-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
HuggingFaceFW/fineweb
Features
16,384
Data Type
float32
Hook Name
blocks.12.hook_resid_post
Hook Layer
12
Architecture
standard
Context Size
1,024
Dataset
Skylion007/openwebtext
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2b-it/12-res-jb/8409?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2b-it/12-res-jb/8409?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
406
+0.12
0.5%
765
+0.10
0.4%
1413
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
406
+0.12
0.02
765
+0.10
0.02
130
+0.10
0.02
Negative Logits
mme
-0.76
tse
-0.76
tanga
-0.74
sii
-0.70
rong
-0.69
michel
-0.67
fta
-0.67
hek
-0.66
kac
-0.65
kien
-0.64
POSITIVE LOGITS
boy
1.39
boys
1.30
Boy
1.28
boy
1.27
boys
1.24
Boy
1.21
Boys
1.15
BOY
1.13
Boys
1.11
BOYS
1.03
Act
ivations
Density 0.054%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
