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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3391
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific measurement and analysis

    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
    EDEFAULT
    -0.64
    sidemargin
    -0.55
    localctx
    -0.54
    iſter
    -0.51
    ſelben
    -0.49
     deflation
    -0.49
    таратура
    -0.48
    Agnes
    -0.48
     instinct
    -0.47
     محفوظة
    -0.47
    POSITIVE LOGITS
    astify
    0.33
    GraphicsUnit
    0.31
     cope
    0.31
    cje
    0.30
    Controllo
    0.28
    ScopeManager
    0.27
    mål
    0.27
     himself
    0.27
     themselves
    0.27
     casse
    0.27
    Activations Density 0.810%

    No Known Activations