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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2245
    Prev
    Next
    INDEX
    Explanations

    elements related to significant events or reactions in dramatic situations

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

    "production" and "productivity"

    np_acts-logits-general · gemini-2.0-flash

    production and productivity

    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
     estekak
    -0.49
    KommentareTeilen
    -0.47
     inesperado
    -0.47
    anskje
    -0.46
    jsxFileName
    -0.45
    cuerdo
    -0.44
    ParallelGroup
    -0.42
    CrossRef
    -0.41
    WithIOException
    -0.40
    toMatchSnapshot
    -0.40
    POSITIVE LOGITS
    IsContent
    0.50
    :✨
    0.45
     Rtl
    0.44
     Innocence
    0.42
    atile
    0.42
    новниш
    0.42
    oa̍t
    0.41
     impairments
    0.41
     незавершена
    0.40
    Xna
    0.39
    Activations Density 0.339%

    No Known Activations