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
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-9B-IT
Residual Stream - 16k
9-GEMMASCOPE-RES-16K
3706
Prev
Next
MODEL
9-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
mathematical expressions and variables in equations
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
The letter "n" followed by specific characters
np_acts-logits-general · gemini-2.0-flash
No Scores
n in various contexts
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-9B-IT @ 9-gemmascope-res-16k
Configuration
google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.9.hook_resid_post
Hook Layer
9
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-9b-it/9-gemmascope-res-16k/3706?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-9b-it/9-gemmascope-res-16k/3706?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
yaf
-0.47
Belajar
-0.45
Pfalz
-0.41
Mühe
-0.41
yue
-0.40
萩
-0.40
ceis
-0.39
gart
-0.39
sweise
-0.39
afari
-0.39
POSITIVE LOGITS
N
1.38
n
1.27
N
1.27
getN
1.10
n
1.05
setN
1.04
NN
0.94
BN
0.93
nn
0.93
NN
0.91
Act
ivations
Density 0.642%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
