© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9418
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on four-digit numeric tokens (i.e. year numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ن
    1.01
    立场
    0.86
     imó
    0.82
     accès
    0.79
     mondiale
    0.79
     ouvrir
    0.79
     libertà
    0.78
     più
    0.77
     extracción
    0.76
     mancanza
    0.76
    POSITIVE LOGITS
    jl
    0.81
    ijas
    0.78
    ным
    0.77
     Рэ
    0.74
    рных
    0.73
    jr
    0.73
     :/
    0.72
     dashing
    0.71
    дает
    0.70
     Toms
    0.70
    Activations Density 0.000%

    No Known Activations