© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38496
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a location or place of interest

    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
    OGND
    -0.90
    ViewFeatures
    -0.67
    :✨
    -0.66
    Хьажоргаш
    -0.61
    Искәрмәләр
    -0.59
    batore
    -0.58
    invokeLater
    -0.58
    الإنجليزية
    -0.57
    ApiModelProperty
    -0.56
     >=",
    -0.56
    POSITIVE LOGITS
     place
    0.92
     Où
    0.81
     spot
    0.75
     tempat
    0.75
     where
    0.74
     endroits
    0.73
    place
    0.72
    Donde
    0.70
     Place
    0.70
    endroit
    0.69
    Activations Density 0.019%

    No Known Activations