© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 7718
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "function" in code-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikispecies
    -0.65
     thither
    -0.56
    ]+=
    -0.54
     sauvages
    -0.52
    География
    -0.52
     Insets
    -0.51
     않았
    -0.51
    ؤلاء
    -0.50
     nobility
    -0.50
     cặp
    -0.50
    POSITIVE LOGITS
     function
    4.50
     Function
    4.13
    function
    4.00
    Function
    3.73
     functions
    3.72
     FUNCTION
    3.70
     Functions
    3.42
     fonction
    3.36
    FUNCTION
    3.30
    functions
    3.22
    Activations Density 0.081%

    No Known Activations