© 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. 9881
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on four-digit numeric tokens (i.e. year/date 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
     Außerdem
    0.18
    ਸ
    0.17
     Gautam
    0.17
     Sachin
    0.17
     Hesap
    0.16
     sorella
    0.16
     Пор
    0.16
     Ком
    0.15
     sogenannten
    0.15
     Фа
    0.15
    POSITIVE LOGITS
    iation
    0.21
    ied
    0.19
    -,
    0.19
    eners
    0.18
    schutz
    0.17
    ies
    0.17
    ities
    0.17
    iest
    0.17
    ers
    0.17
    ative
    0.17
    Activations Density 0.000%

    No Known Activations