Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13801
    Prev
    Next
    INDEX
    Explanations

    references to time intervals, specifically days, weeks, and related activities

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

    days, weeks, and time intervals

    np_acts-logits-general · gemini-2.0-flash

    weekly intervals or days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    Year
    -0.88
     Year
    -0.81
    year
    -0.81
     year
    -0.80
    getYear
    -0.79
     annually
    -0.74
     YEAR
    -0.73
    Annual
    -0.68
     Annual
    -0.68
     Tahun
    -0.68
    POSITIVE LOGITS
     week
    2.28
    week
    1.91
     WEEK
    1.87
     Week
    1.86
    Week
    1.77
     weeks
    1.72
     semaine
    1.71
    WEEK
    1.66
     semana
    1.64
     Woche
    1.55
    Activations Density 0.376%

    No Known Activations