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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 7324
    Prev
    Next
    INDEX
    Explanations

    technical terminology and specific terms related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    caccio
    -0.54
     eventId
    -0.49
     gând
    -0.49
     sélection
    -0.48
    Дереккөздер
    -0.47
     kautta
    -0.46
    niająca
    -0.45
    Билгалдахарш
    -0.45
     assister
    -0.45
    ونز
    -0.44
    POSITIVE LOGITS
    ModelAdmin
    0.79
    endphp
    0.70
    ved
    0.69
     &___
    0.69
     StatefulWidget
    0.67
     createSlice
    0.64
     DbType
    0.63
     oprot
    0.63
    lik
    0.62
    ves
    0.61
    Activations Density 1.874%

    No Known Activations