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. 7-GEMMASCOPE-RES-16K
    6. 14806
    Prev
    Next
    INDEX
    Explanations

    HTML table elements and their associated structures

    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
    Географиясе
    -0.73
    oa̍t
    -0.70
    ArrowToggle
    -0.70
     متعلقه
    -0.68
    Източници
    -0.66
    Хьажоргаш
    -0.65
    ỡng
    -0.64
    省市镇
    -0.63
     hire
    -0.63
    сылкі
    -0.62
    POSITIVE LOGITS
    <table>
    3.41
    <tbody>
    1.41
    </table>
    1.11
    <caption>
    1.05
    <h6>
    1.02
    <thead>
    0.99
    RectangleBorder
    0.86
    <th>
    0.83
    </thead>
    0.81
    الدراسه
    0.80
    Activations Density 0.084%

    No Known Activations