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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1799
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically seasons and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    σθαι
    -0.79
    enumi
    -0.76
    creativecommons
    -0.72
     виправивши
    -0.71
    :✨
    -0.69
    HasForeignKey
    -0.66
     وصلة
    -0.66
    unjang
    -0.65
     utafitiHapana
    -0.65
     ویکی‌پدیا
    -0.64
    POSITIVE LOGITS
    年
    0.85
     Jaffe
    0.66
     срока
    0.62
    بوابة
    0.62
    ген
    0.62
     April
    0.60
    月
    0.58
     January
    0.58
     December
    0.57
    behörde
    0.57
    Activations Density 0.003%

    No Known Activations