Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 14979
    Prev
    Next
    INDEX
    Explanations

    special characters and syntax associated with code

    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
    :✨
    -0.99
    rrggbb
    -0.83
     ProtoMessage
    -0.76
     noDo
    -0.75
    省市镇
    -0.69
    tonode
    -0.66
    setVerticalGroup
    -0.62
    oredCriteria
    -0.62
    expandindo
    -0.62
    hoku
    -0.62
    POSITIVE LOGITS
     StatefulWidget
    0.80
     EdgeInsets
    0.67
     ekst
    0.59
    EdgeInsets
    0.59
    gapa
    0.51
    ^(@)
    0.50
     MethodInfo
    0.50
    namiento
    0.49
     setTime
    0.48
    TextWatcher
    0.48
    Activations Density 0.001%

    No Known Activations