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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2853
    Prev
    Next
    INDEX
    Explanations

    patterns or structures related to programming code or syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.75
     unknownFields
    -0.73
    хьтан
    -0.72
    opsida
    -0.67
     "..\..\..\
    -0.66
    WithIOException
    -0.62
    য়ে
    -0.60
    Filmografia
    -0.59
    protoimpl
    -0.58
    blende
    -0.57
    POSITIVE LOGITS
    GraphicsUnit
    0.81
    principalColumn
    0.74
    saraba
    0.65
     مشين
    0.64
    enderror
    0.59
    :+:
    0.59
    setcounter
    0.59
    mathrm
    0.57
     dė
    0.57
    reportWebVitals
    0.56
    Activations Density 0.026%

    No Known Activations