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. 12-GEMMASCOPE-RES-16K
    6. 9859
    Prev
    Next
    INDEX
    Explanations

    themes of hope, faith, and divine reassurance amidst challenges or uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Jeografia
    -0.61
    tan
    -0.56
    至此
    -0.53
    ῖς
    -0.52
     mày
    -0.51
     resourceCulture
    -0.51
     tant
    -0.50
     εφ
    -0.50
    жели
    -0.50
    OfMonth
    -0.49
    POSITIVE LOGITS
     kasarigan
    0.66
     Roskov
    0.59
    ConstraintMaker
    0.57
    criptures
    0.57
     TextAlign
    0.56
    دانشنامهٔ
    0.53
    :][
    0.52
    клопе
    0.51
    IMDG
    0.49
    MessageDigest
    0.49
    Activations Density 0.259%

    No Known Activations