© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 10367
    Prev
    Next
    INDEX
    Explanations

    words and phrases that pertain to coverage or the act of covering topics or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    covers a range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regalías
    -0.52
     Garantía
    -0.50
    談社
    -0.49
    Numerology
    -0.48
     newOwner
    -0.46
     فريبيس
    -0.45
     SCIENT
    -0.41
    ionage
    -0.41
     confusión
    -0.41
     confirmer
    -0.40
    POSITIVE LOGITS
     topics
    0.72
    Covered
    0.63
     everything
    0.63
    Topics
    0.62
     areas
    0.58
    tly
    0.57
     Covered
    0.56
     coverage
    0.55
     EconPapers
    0.54
     covered
    0.54
    Activations Density 0.011%

    No Known Activations