© 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. 31-GEMMASCOPE-RES-131K
    6. 44548
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions in JavaFX and GTK

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

    gtk ui functions

    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
    頭
    -0.32
    unknownFields
    -0.31
     hereof
    -0.30
    GMENT
    -0.29
     vů
    -0.29
    큼
    -0.29
    头
    -0.29
    DEF
    -0.28
    oa̍t
    -0.28
     貼
    -0.28
    POSITIVE LOGITS
     javafx
    1.11
    RegressionTest
    0.58
     FX
    0.58
    WebElementEntity
    0.56
    FX
    0.55
    fx
    0.55
     defaultstate
    0.55
     MainAxisSize
    0.54
    primaryStage
    0.53
    Fx
    0.53
    Activations Density 0.001%

    No Known Activations