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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 64931
    Prev
    Next
    INDEX
    Explanations

    references to the act of lending or providing assistance

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

    lend itself, lends credibility, lent additional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     Kraus
    -0.59
    Telefax
    -0.54
     Moreira
    -0.54
    ────────
    -0.50
     "
    -0.49
     Koval
    -0.48
    idł
    -0.48
     Pas
    -0.48
     Ortega
    -0.47
    makedirs
    -0.47
    POSITIVE LOGITS
     Lend
    1.09
     Lending
    1.03
     lend
    1.02
    lend
    0.96
     lending
    0.90
     lends
    0.85
     Lender
    0.77
     lent
    0.76
     préstamos
    0.68
     lender
    0.66
    Activations Density 0.003%

    No Known Activations