© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27820
    Prev
    Next
    INDEX
    Explanations

    terminology related to torque and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    target, expected, or predicted values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.79
    AndEndTag
    -0.70
    ArrowToggle
    -0.68
    Espèce
    -0.67
    تقاوى
    -0.66
    expandindo
    -0.66
    AntiForgeryToken
    -0.61
     مشين
    -0.60
    enumii
    -0.59
    FieldBuilder
    -0.59
    POSITIVE LOGITS
    通りの
    0.52
    通り
    0.49
    WithIdentifier
    0.48
     đoán
    0.47
     corrected
    0.47
    대로
    0.47
     Consig
    0.46
     corrig
    0.46
    nosed
    0.45
     Soll
    0.45
    Activations Density 0.118%

    No Known Activations