© 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. 30-GEMMASCOPE-RES-16K
    11. 7507
    Prev
    Next
    INDEX
    Explanations

    conditions and actions related to regulatory measures and their impact

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

    Actions being stopped or suspended

    np_acts-logits-general · gemini-2.0-flash

    stopping or pausing actions and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    krä
    -0.33
     رد
    -0.31
     dren
    -0.31
    üman
    -0.30
    %%
    -0.29
     Schw
    -0.29
    出版年
    -0.28
    ULO
    -0.28
     borra
    -0.28
     Pire
    -0.27
    POSITIVE LOGITS
     pause
    1.98
     paused
    1.91
     pausing
    1.80
     halted
    1.73
     pauses
    1.72
     halt
    1.69
     Pause
    1.68
    pause
    1.66
     stopped
    1.65
     stop
    1.63
    Activations Density 0.561%

    No Known Activations