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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38870
    Prev
    Next
    INDEX
    Explanations

    the presence of the beginning of sections or paragraphs in a text

    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
    NegativeButton
    -0.85
    HtmlAttribute
    -0.84
    ♥♥
    -0.78
     Iraq
    -0.78
    ⇐
    -0.78
    клопе
    -0.77
     Bowles
    -0.75
    NamedQueries
    -0.75
     estimés
    -0.74
    */}
    -0.73
    POSITIVE LOGITS
     Merit
    0.92
     merit
    0.81
     Cellulose
    0.79
    merit
    0.77
     Kild
    0.71
     Eul
    0.68
    ufnahme
    0.67
    getProperties
    0.66
     Carleton
    0.66
    ymce
    0.66
    Activations Density 0.071%

    No Known Activations