© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 9833
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax in programming languages, particularly related to custom types and function definitions

    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
    hitheatre
    -0.57
     banheiro
    -0.54
     Mexicano
    -0.52
     Laplacian
    -0.50
     Secretaría
    -0.50
     ansatte
    -0.49
     düğün
    -0.49
     fogo
    -0.48
    ingway
    -0.48
     spirituale
    -0.48
    POSITIVE LOGITS
    AxisAlignment
    0.92
    abestanden
    0.82
    ::{
    0.81
     חיצוניים
    0.78
    GraphicsUnit
    0.78
     MainAxisSize
    0.77
    Искәрмәләр
    0.72
     StatefulWidget
    0.70
     MotionEvent
    0.70
    ::*;
    0.70
    Activations Density 0.102%

    No Known Activations