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
10022
Prev
Next
MODEL
12-res-jb
Source/SAE
INDEX
Go
Explanations
names of mythological or fictional characters and places
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
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/10022?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/10022?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
674
+0.53
2.0%
1967
+0.17
0.6%
382
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1597
+0.53
0.04
1213
+0.17
0.07
227
+0.10
0.07
Negative Logits
wien
-3.74
effe
-3.68
fta
-3.53
mef
-3.53
fte
-3.49
ftu
-3.48
aen
-3.48
„,
-3.42
squa
-3.39
fto
-3.35
POSITIVE LOGITS
<bos>
2.14
1.10
,
1.03
.
1.03
in
1.00
1.00
;
1.00
...
0.99
am
0.98
for
0.98
Act
ivations
Density 0.638%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
