© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3554
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions related to data types and structures

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

    Javascript/typescript type annotations and keywords

    np_acts-logits-general · gemini-2.0-flash

    oneof, is, nested, function, or boolean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     الاطلاع
    -0.56
     Commencez
    -0.53
     cheeks
    -0.49
    xmlns
    -0.44
     coloro
    -0.42
     tromper
    -0.42
     correspondiente
    -0.42
     lname
    -0.42
     gambe
    -0.42
    ⓧ
    -0.41
    POSITIVE LOGITS
     estekak
    0.81
     שוליים
    0.77
     ModelExpression
    0.71
     חיצוניים
    0.70
     multi
    0.67
    aarrggbb
    0.66
     استنادى
    0.65
     binary
    0.65
     enums
    0.64
     compound
    0.63
    Activations Density 0.811%

    No Known Activations