© 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. 37474
    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
    out
    -0.35
    medriver
    -0.33
     forever
    -0.33
    #
    -0.30
    xfd
    -0.29
     still
    -0.29
     encima
    -0.29
     instead
    -0.28
    new
    -0.28
    ordin
    -0.28
    POSITIVE LOGITS
    BuildContext
    4.38
     EdgeInsets
    1.16
     BoxDecoration
    1.13
    MigrationBuilder
    1.08
    ChildScrollView
    1.05
     kasarigan
    1.03
     propOrder
    0.96
    setVerticalGroup
    0.94
     StatelessWidget
    0.94
     للاسماء
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.