© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15776
    Prev
    Next
    INDEX
    Explanations

    instances of structured data or placeholders in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.75
     
    -0.66
     “
    -0.59
    (
    -0.57
     mochila
    -0.56
     "
    -0.56
     stronie
    -0.56
     (
    -0.55
     Mooney
    -0.54
    чан
    -0.54
    POSITIVE LOGITS
    PerformLayout
    1.30
     وتسجيلات
    1.23
     متعلقه
    1.16
    </caption>
    1.12
     المعيارى
    1.09
    ."</
    1.05
    <tbody>
    1.02
    </thead>
    1.00
     صوتيه
    1.00
    ……"
    0.99
    Activations Density 0.133%

    No Known Activations