© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 63660
    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
     types
    -0.40
     extranjera
    -0.38
     disfraces
    -0.36
     electrico
    -0.36
     or
    -0.35
     takı
    -0.35
    NegativeButton
    -0.34
    PositiveButton
    -0.34
     aportes
    -0.34
     jenis
    -0.33
    POSITIVE LOGITS
    cshtml
    3.52
    SourceChecksum
    1.12
    jspx
    0.91
    InjectAttribute
    0.90
    endphp
    0.88
     ExecuteAsync
    0.88
    adaptiveStyles
    0.87
    ViewFeatures
    0.86
     initComponents
    0.81
    IUrlHelper
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.