Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8619
    Prev
    Next
    INDEX
    Explanations

    statistical measures related to health metrics and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.60
     дописавши
    -0.59
    icato
    -0.52
    dets
    -0.52
    tomans
    -0.49
     Atoms
    -0.49
    Aholisi
    -0.49
    лтемелер
    -0.48
    约
    -0.48
    ticale
    -0.48
    POSITIVE LOGITS
    migrationBuilder
    0.45
    IonicModule
    0.39
     defaultstate
    0.38
     spared
    0.37
    CopyWith
    0.35
    Citiți
    0.33
    ::::::::
    0.32
    labelledby
    0.31
    UserScript
    0.31
     OnInit
    0.30
    Activations Density 1.134%

    No Known Activations