© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 13183
    Prev
    Next
    INDEX
    Explanations

    references to programming functions and concepts related to coding

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Negative Logits
     gsx
    -0.64
     keten
    -0.59
    %=
    -0.59
    Cyfeiriadau
    -0.59
    reciate
    -0.57
     %(
    -0.55
     zirc
    -0.55
    tened
    -0.54
     Daz
    -0.54
     Plut
    -0.54
    POSITIVE LOGITS
     Function
    0.98
     funcion
    0.97
     function
    0.96
    func
    0.94
    function
    0.93
     FUNCTION
    0.92
     fonction
    0.92
    funk
    0.91
    Function
    0.90
    FUNCTION
    0.89
    Activations Density 3.006%

    No Known Activations