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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7411
    Prev
    Next
    INDEX
    Explanations

    references to various job opportunities and demographics

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

    First tokens in web navigation elements, menu items, or demographic category listings in structured web page layouts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    
    -0.71
     ब्रेकडाउन
    -0.68
     betweenstory
    -0.66
    ftagPool
    -0.66
     Chwiliwch
    -0.66
     AssemblyVersion
    -0.65
    oa̍t
    -0.61
    ArrowToggle
    -0.57
    цездатний
    -0.57
    Jereo
    -0.56
    POSITIVE LOGITS
    Datuak
    0.40
     cheers
    0.38
    folger
    0.34
     cooking
    0.34
    fiche
    0.33
     кое
    0.32
    alogy
    0.32
    houd
    0.32
    taining
    0.32
     odd
    0.32
    Activations Density 0.194%

    No Known Activations