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. 21-GEMMASCOPE-RES-16K
    6. 12526
    Prev
    Next
    INDEX
    Explanations

    HTML table structures and elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Demografía
    -0.64
    Izvori
    -0.56
     doInBackground
    -0.54
    ViewBag
    -0.53
     πρό
    -0.52
     is
    -0.51
     par
    -0.51
    ,
    -0.50
    s
    -0.50
    setupUi
    -0.50
    POSITIVE LOGITS
    <tbody>
    2.08
    <thead>
    1.29
    <caption>
    1.17
    </table>
    1.10
    findpost
    1.04
    </caption>
    1.02
    </thead>
    1.00
    <table>
    0.93
    </tr>
    0.88
     myſelf
    0.87
    Activations Density 0.030%

    No Known Activations