© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10736
    Prev
    Next
    INDEX
    Explanations

    words related to capturing or seizing something, particularly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consultato
    -0.57
     Sce
    -0.56
    esModule
    -0.48
     dilu
    -0.48
     Mines
    -0.48
     biochemical
    -0.48
    mawia
    -0.47
    空白
    -0.47
    Fullscreen
    -0.47
    HSSF
    -0.46
    POSITIVE LOGITS
     capturing
    1.05
     betweenstory
    0.88
     capture
    0.86
     Capture
    0.82
     AssemblyCulture
    0.81
    tagHelperRunner
    0.77
     booking
    0.77
    webElementXpaths
    0.77
    Carcinogenicity
    0.76
     CAPT
    0.76
    Activations Density 0.046%

    No Known Activations