© 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. 4557
    Prev
    Next
    INDEX
    Explanations

    references to prominent individuals or key players in various contexts

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

    influential people and actors

    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
     parallèle
    -0.43
     Behandlung
    -0.41
     scolaires
    -0.38
     Sicherung
    -0.38
     invasión
    -0.38
     cardiaque
    -0.36
     resolución
    -0.36
     frenos
    -0.35
     syarat
    -0.35
     aceptación
    -0.35
    POSITIVE LOGITS
     EconPapers
    0.81
    AnchorStyles
    0.71
     eventName
    0.67
    ScopeManager
    0.64
    AddHtmlAttribute
    0.63
    argout
    0.61
    InjectAttribute
    0.60
    rungsseite
    0.60
    Datuak
    0.60
    bootstrapcdn
    0.58
    Activations Density 0.015%

    No Known Activations