© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 63455
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to scientific and programming contexts

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

    gliding, ffmpeg, prevalence, guidelines, Erie, Binding

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     numberOfRows
    -0.42
    //
    -0.34
     South
    -0.33
     remembered
    -0.33
     boxes
    -0.32
    onatos
    -0.32
    #
    -0.32
     position
    -0.32
    ţilor
    -0.32
     cars
    -0.31
    POSITIVE LOGITS
    glide
    2.06
    Glide
    1.67
     Glide
    1.49
     glide
    1.27
     glides
    0.84
     gliding
    0.78
    :✨
    0.75
    ConstraintMaker
    0.73
    gli
    0.70
    OGND
    0.70
    Activations Density 0.000%

    No Known Activations