© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 16959
    Prev
    Next
    INDEX
    Explanations

    sections detailing ethical considerations and consent processes in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following specific guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.70
    expandindo
    -0.49
     estekak
    -0.40
    ConstraintMaker
    -0.38
    webElementXpaths
    -0.37
    Easily
    -0.36
     <<<<<<<<<<<<<<
    -0.36
    AutoScaleMode
    -0.35
     defaultstate
    -0.35
    /*
    -0.35
    POSITIVE LOGITS
     according
    1.76
     accordance
    1.48
    according
    1.46
     zgodnie
    1.37
     conformément
    1.34
     согласно
    1.27
     volgens
    1.26
     según
    1.23
     selon
    1.22
     acordo
    1.22
    Activations Density 0.152%

    No Known Activations