© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14427
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to scientific research methodology and specifications

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

    size or magnitude

    np_acts-logits-general · gemini-2.0-flash

    small, petite, diminutive, smaller

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    stwie
    -0.31
    inephrine
    -0.29
     symptoms
    -0.29
     symptom
    -0.29
     Administración
    -0.28
    เสีย
    -0.28
    symptoms
    -0.28
    uanto
    -0.27
     Matériau
    -0.27
     cố
    -0.27
    POSITIVE LOGITS
    AndEndTag
    0.83
     diminutive
    0.73
     sederhana
    0.73
    Smaller
    0.68
    setVerticalGroup
    0.68
    TypedDataSet
    0.68
    smaller
    0.67
    rungsseite
    0.67
     smaller
    0.66
     petite
    0.65
    Activations Density 0.655%

    No Known Activations