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 - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13802
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to set theory and operations

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

    Mathematical set notation

    np_acts-logits-general · gemini-2.0-flash

    set union and intersection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.75
     jspb
    -0.69
     MainAxisSize
    -0.66
     numberWith
    -0.64
     BoxFit
    -0.62
    protoc
    -0.61
    ConstraintMaker
    -0.61
     ویکی‌پدیای
    -0.59
     StatefulWidget
    -0.58
     ModelExpression
    -0.58
    POSITIVE LOGITS
     union
    1.17
     Union
    1.01
    Union
    0.99
    union
    0.99
     UNION
    0.97
     intersection
    0.95
    UNION
    0.88
     intersect
    0.83
    intersection
    0.79
     intersected
    0.78
    Activations Density 0.744%

    No Known Activations