© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15477
    Prev
    Next
    INDEX
    Explanations

    references to time and dates in various contexts

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

    Time periods ("year", "day", "month")

    np_acts-logits-general · gemini-2.0-flash

    time of year or day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iprot
    -0.71
     للاسماء
    -0.67
    AntiForgeryToken
    -0.55
     propOrder
    -0.55
     noqa
    -0.55
    InvalidProtocol
    -0.54
    ArgsConstructor
    -0.54
    elemField
    -0.54
    canestro
    -0.51
    AccessorTable
    -0.50
    POSITIVE LOGITS
     year
    1.25
     day
    0.95
    year
    0.93
     YEAR
    0.89
     jaar
    0.87
     month
    0.87
     año
    0.86
     année
    0.81
     Year
    0.81
     season
    0.81
    Activations Density 0.121%

    No Known Activations