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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 36748
    Prev
    Next
    INDEX
    Explanations

    colons and their associated context within programming or code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORAGE
    -0.57
    tsburgh
    -0.49
    ùng
    -0.48
    getConfiguration
    -0.47
    piratory
    -0.47
    Console
    -0.47
    versario
    -0.47
    stdarg
    -0.46
    SqlSession
    -0.46
    ябре
    -0.46
    POSITIVE LOGITS
    ::~
    0.85
    isContained
    0.73
    Parcelize
    0.66
     }}"></
    0.64
    Datuak
    0.64
    ArgsConstructor
    0.63
    DeleteBehavior
    0.60
    Filmografie
    0.59
    enderror
    0.59
    )|^{
    0.59
    Activations Density 0.013%

    No Known Activations