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 - 131k
20-GEMMASCOPE-RES-131K
23475
Prev
Next
MODEL
20-gemmascope-res-131k
Source/SAE
INDEX
Go
Explanations
references to cycles and cycle-related terminology in scientific contexts
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
Comparing With
GEMMA-2-9B-IT @ 20-gemmascope-res-131k
Configuration
google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
131,072
Data Type
float32
Hook Name
blocks.20.hook_resid_post
Hook Layer
20
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/20-gemmascope-res-131k/23475?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/20-gemmascope-res-131k/23475?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
man
-0.44
and
-0.43
MAN
-0.41
white
-0.41
a
-0.40
ness
-0.39
min
-0.39
A
-0.39
a
-0.39
un
-0.39
POSITIVE LOGITS
CYCLE
1.30
cycle
1.28
Cycle
1.26
cycle
1.20
Cycle
1.19
cycles
1.18
Cycles
1.12
CYCLE
1.07
cycles
1.05
Cycles
1.03
Act
ivations
Density 0.023%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
