© 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. 42010
    Prev
    Next
    INDEX
    Explanations

    elements related to class definitions and CSS in a programming context

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

    css classes

    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
     last
    -0.33
    ream
    -0.32
    writeFileSync
    -0.31
    调
    -0.31
    вающих
    -0.31
     
    -0.31
     turn
    -0.31
     enthusiastic
    -0.30
     contaminated
    -0.29
     no
    -0.29
    POSITIVE LOGITS
     useStyles
    0.81
    AnimationsModule
    0.75
    الحياه
    0.74
     gyhoeddwyd
    0.73
    хьтан
    0.72
    SharedDtor
    0.70
    DockStyle
    0.69
    Personendaten
    0.68
    ConstraintMaker
    0.65
     makeStyles
    0.64
    Activations Density 0.002%

    No Known Activations