© 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. 12925
    Prev
    Next
    INDEX
    Explanations

    terms related to dimensions or measurements, particularly focusing on "span."

    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
     Kurtz
    -0.48
    hø
    -0.48
    améli
    -0.48
     corrientes
    -0.48
     jueces
    -0.48
    寄せ
    -0.47
    ppi
    -0.47
     aux
    -0.46
     [
    -0.46
    helper
    -0.46
    POSITIVE LOGITS
     Span
    0.96
     Houſe
    0.93
     auffi
    0.93
    ConstraintMaker
    0.90
     myſelf
    0.88
     span
    0.86
    EDEFAULT
    0.85
     Anſ
    0.85
     SPAN
    0.84
     purpoſe
    0.82
    Activations Density 0.054%

    No Known Activations