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. 0-GEMMASCOPE-RES-16K
    6. 6354
    Prev
    Next
    INDEX
    Explanations

    references to daily or regular activities and human experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.65
    lète
    -0.61
    Espèce
    -0.59
    unhofer
    -0.58
    barbie
    -0.58
    toje
    -0.55
     chi̍t
    -0.53
    تقاوى
    -0.53
    hringer
    -0.52
     surla
    -0.51
    POSITIVE LOGITS
     daily
    1.35
    Daily
    1.29
     Daily
    1.25
    daily
    1.21
    DAILY
    1.05
     DAILY
    1.03
     Everyday
    0.99
     everyday
    0.93
    Everyday
    0.90
    每日
    0.89
    Activations Density 0.133%

    No Known Activations