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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 15930
    Prev
    Next
    INDEX
    Explanations

    distinct structures or symbols used in programming or data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.71
     propOrder
    -0.67
    GraphicsUnit
    -0.66
     muualla
    -0.65
     grà
    -0.64
    ProgressHUD
    -0.64
    CodeAttribute
    -0.63
     بتاريخ
    -0.62
    endphp
    -0.61
    LookAnd
    -0.60
    POSITIVE LOGITS
     VIAF
    0.60
     químico
    0.54
    %">
    0.52
    VIAF
    0.47
    monium
    0.47
     befolk
    0.47
     químicos
    0.46
     tider
    0.46
     NSCoder
    0.46
    زيل
    0.45
    Activations Density 0.240%

    No Known Activations