© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 49670
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KURZBESCHREIBUNG
    -0.71
    ChildScrollView
    -0.65
    GEBURTSDATUM
    -0.57
    AntiForgeryToken
    -0.57
     Administrativna
    -0.56
    parsedMessage
    -0.56
    printStackTrace
    -0.56
    Personendaten
    -0.55
    FXML
    -0.54
    .*")]
    -0.53
    POSITIVE LOGITS
     CreateTagHelper
    0.45
    AccessorTable
    0.41
     __
    0.36
    GIVEREF
    0.35
     denoted
    0.33
     للاسماء
    0.32
    DoubleQuotes
    0.32
    ніципалі
    0.31
     صوتيه
    0.31
    $^
    0.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.