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. 16-GEMMASCOPE-RES-16K
    6. 12587
    Prev
    Next
    INDEX
    Explanations

    dates and times related to events or actions

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

    Dates, often with the word "on" or "dated"

    np_acts-logits-general · gemini-2.0-flash

    months followed by dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -1.09
    tagHelperRunner
    -0.90
    MigrationBuilder
    -0.79
    NameInMap
    -0.79
    исленность
    -0.79
    mybatisplus
    -0.78
    InitVars
    -0.77
    يميديا
    -0.74
     Biôgrafia
    -0.73
     تضيفلها
    -0.73
    POSITIVE LOGITS
     April
    0.82
     June
    0.79
     September
    0.74
     March
    0.73
     January
    0.71
     May
    0.70
     August
    0.69
     
    0.69
     October
    0.69
     July
    0.67
    Activations Density 0.183%

    No Known Activations