© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3117
    Prev
    Next
    INDEX
    Explanations

    content that is classified as offensive or contains warnings about sensitive material

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    content warnings and disclaimers about offensive, inappropriate, or restricted material.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    DockStyle
    -0.33
     cherchez
    -0.30
     bingung
    -0.29
    γνω
    -0.29
    GUILayout
    -0.29
     battre
    -0.29
    hubung
    -0.28
     envy
    -0.26
     dogged
    -0.26
    说明
    -0.26
    POSITIVE LOGITS
    sensitive
    1.02
     objectionable
    1.01
     offensive
    1.01
     censored
    0.99
    offensive
    0.99
     sensitive
    0.96
     inappropriate
    0.96
    Offensive
    0.94
    ensitive
    0.93
    Sensitive
    0.92
    Activations Density 0.427%

    No Known Activations