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. 36537
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax related to event handling or timers

    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
    SourceChecksum
    -1.14
    LookAnd
    -1.08
    tagHelperRunner
    -1.02
    invokeLater
    -0.90
     resourceCulture
    -0.90
    FieldBuilder
    -0.87
    存于互联网档案馆
    -0.86
    XmlEnum
    -0.85
     propOrder
    -0.84
    AccessorTable
    -0.82
    POSITIVE LOGITS
     tình
    0.45
    );
    0.44
    tuber
    0.44
     ...
    0.41
     ͜ʖ
    0.40
    tableView
    0.39
    ";
    0.39
     sarung
    0.38
    .);
    0.37
    daq
    0.37
    Activations Density 0.046%

    No Known Activations