© 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. 9121
    Prev
    Next
    INDEX
    Explanations

    references to swords or sword-related concepts

    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
     propOrder
    -1.11
    SourceChecksum
    -1.03
    parsedMessage
    -0.98
    UnusedPrivate
    -0.94
    DeleteBehavior
    -0.93
     ویکی‌پدیا
    -0.90
    Попис
    -0.90
    niająca
    -0.87
     '\\;'
    -0.86
    complexContent
    -0.83
    POSITIVE LOGITS
     sword
    1.01
     Sword
    0.99
    Sword
    0.96
     swords
    0.91
     Swords
    0.88
    sword
    0.87
    slice
    0.77
     slicing
    0.74
    Slice
    0.73
     slice
    0.69
    Activations Density 0.080%

    No Known Activations