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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-GEMMASCOPE-RES-16K
    6. 4506
    Prev
    Next
    INDEX
    Explanations

    programming or technical terms related to data structure and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.24
    migrationBuilder
    -1.04
    CloseOperation
    -0.99
    +#+#
    -0.97
     cherchés
    -0.93
     समीक्षाओं
    -0.88
     BoxDecoration
    -0.86
     StatefulWidget
    -0.83
    VIAF
    -0.83
    :✨
    -0.80
    POSITIVE LOGITS
     conversion
    0.59
     conversions
    0.54
    Conversion
    0.52
     Jo
    0.47
     conver
    0.46
     Conversion
    0.45
    Jo
    0.44
    Conver
    0.44
     representation
    0.43
    kaufs
    0.41
    Activations Density 0.499%

    No Known Activations