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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15982
    Prev
    Next
    INDEX
    Explanations

    references to Slavic mythology and its key figures

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

    Eastern European countries/regions

    np_acts-logits-general · gemini-2.0-flash

    Slavic Eastern Europe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.52
    RegressionTest
    -0.50
     estekak
    -0.50
    Diweddarwch
    -0.50
    UrlResolution
    -0.49
     Мексика
    -0.49
    VersionUID
    -0.49
    delwed
    -0.48
    efeller
    -0.48
    adaptiveStyles
    -0.48
    POSITIVE LOGITS
     Slavic
    0.91
     Russian
    0.88
     Ukrainian
    0.87
     Ukraine
    0.84
     Polish
    0.77
    Slav
    0.76
     Slav
    0.74
     Russia
    0.73
     Ukrainians
    0.72
     Soviet
    0.70
    Activations Density 0.491%

    No Known Activations