© 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 EvalsExportsAPI 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. 10870
    Prev
    Next
    INDEX
    Explanations

    syntax elements typical in markup or programming languages

    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
     المعيارى
    -0.78
     resourceCulture
    -0.74
    Lähteet
    -0.69
     ProtoMessage
    -0.67
    ništvo
    -0.64
     iArr
    -0.63
    SharedDtor
    -0.61
    NUMX
    -0.60
    قایناقلار
    -0.59
     ‍
    -0.59
    POSITIVE LOGITS
    <
    3.52
     <
    3.33
    .<
    2.97
    :<
    2.97
    )<
    2.94
    ,<
    2.81
    -<
    2.81
    /<
    2.80
    ?<
    2.72
    !<
    2.69
    Activations Density 0.216%

    No Known Activations