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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13-GEMMASCOPE-RES-65K
    6. 57005
    Prev
    Next
    INDEX
    Explanations

    occurrences of header file references in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    曖昧さ回避
    -0.75
    aarrggbb
    -0.71
    onAttach
    -0.69
    queryInterface
    -0.69
     ProtoMessage
    -0.62
    riwal
    -0.61
     ModelExpression
    -0.61
    protoimpl
    -0.60
    DoubleQuotes
    -0.60
    ош
    -0.59
    POSITIVE LOGITS
    hpp
    1.82
    Tikang
    0.94
    HPP
    0.78
    urati
    0.73
     Theſe
    0.73
     themſelves
    0.69
     erv
    0.68
     viſ
    0.67
    ̍t
    0.67
    Datuak
    0.67
    Activations Density 0.002%

    No Known Activations