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-2-2B
Residual Stream - 16k
5-GEMMASCOPE-RES-16K
12165
Prev
Next
MODEL
5-gemmascope-res-16k
Source/SAE
INDEX
Go
Explanations
comparative adjectives indicating a higher degree
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-2-2B @ 5-gemmascope-res-16k
Configuration
google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
How To Load
Prompts (Dashboard)
36,864 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.5.hook_resid_post
Hook Layer
5
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-2-2b/5-gemmascope-res-16k/12165?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/5-gemmascope-res-16k/12165?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
يتيمه
-0.75
HSP
-0.65
zell
-0.65
FE
-0.61
Fox
-0.61
ẻo
-0.60
ical
-0.60
സ
-0.58
P
-0.56
dali
-0.56
POSITIVE LOGITS
THAN
1.95
Than
1.68
than
1.62
Than
1.59
THAN
1.43
than
1.35
än
1.20
OrEqualTo
1.11
niż
1.10
než
1.06
Act
ivations
Density 0.102%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
