© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 6656
    Prev
    Next
    INDEX
    Explanations

    code structure and class declarations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.75
     ModelExpression
    -0.66
    ThroughAttribute
    -0.57
    Hochspringen
    -0.49
     Infórmanos
    -0.48
    uxxxx
    -0.47
    хівовано
    -0.46
    تقاوى
    -0.46
     Private
    -0.46
     برانيه
    -0.45
    POSITIVE LOGITS
     partial
    0.60
    partial
    0.54
    bibfield
    0.46
     sealed
    0.45
     sellado
    0.42
     partielle
    0.42
    Partial
    0.41
     Partial
    0.40
    Brief
    0.38
    ésus
    0.37
    Activations Density 0.175%

    No Known Activations