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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10327
    Prev
    Next
    INDEX
    Explanations

    technical terms and classes related to programming and software development

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

    enum-like types

    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
    BindView
    -0.37
    Véxase
    -0.36
    querySelector
    -0.33
     Pesca
    -0.31
    AppComponent
    -0.31
     decorados
    -0.30
     decoradas
    -0.30
     payé
    -0.29
     NgModule
    -0.29
     Teilen
    -0.29
    POSITIVE LOGITS
    IntoConstraints
    0.81
     BoxFit
    0.71
    ValueStyle
    0.71
    DockStyle
    0.71
     MainAxisSize
    0.68
     GenerationType
    0.65
     TextInputType
    0.63
     للاسماء
    0.62
     kasarigan
    0.61
     ujednoznacz
    0.61
    Activations Density 0.002%

    No Known Activations