© 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. 9-GEMMASCOPE-RES-131K
    11. 102394
    Prev
    Next
    INDEX
    Explanations

    key terms related to legal actions and responsibilities

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

    developed, accomplished, savable, measured, testified, properties, existed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    FileInputStream
    -0.42
     □
    -0.39
    
    -0.39
    heel
    -0.38
     Deeds
    -0.38
    ttino
    -0.37
     Incar
    -0.37
    chaft
    -0.37
     ?.
    -0.36
     savings
    -0.36
    POSITIVE LOGITS
    findpost
    0.62
    webElementXpaths
    0.62
    ConstraintMaker
    0.60
     Taktlose
    0.59
    лтамалар
    0.59
     ModelExpression
    0.58
    تقاوى
    0.57
    󠁴
    0.56
    ItemBackground
    0.56
     ivelany
    0.55
    Activations Density 0.329%

    No Known Activations