© 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. 24-GEMMASCOPE-RES-16K
    11. 7609
    Prev
    Next
    INDEX
    Explanations

    specific names or terminologies related to various fields and subjects

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

    starting with "Con," "En," "Po," "St," "Ex," or "Mag"

    np_acts-logits-general · gemini-2.0-flash

    Constr, Enhancer, starch, exhibits, Enron, Guzman, Collett

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    necedor
    -0.95
    hiculo
    -0.80
    достатки
    -0.78
    здрав
    -0.77
    tymologie
    -0.75
    ocidad
    -0.75
    dasarkan
    -0.74
    ongiorno
    -0.72
    guien
    -0.72
    cyklopedia
    -0.71
    POSITIVE LOGITS
    withstanding
    1.03
    NUMX
    0.85
    foundland
    0.82
    giveness
    0.81
    которые
    0.80
    itudinal
    0.73
    StreetMap
    0.72
    raits
    0.72
    ergies
    0.69
    quakes
    0.67
    Activations Density 0.485%

    No Known Activations