© 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. 13-GEMMASCOPE-RES-65K
    11. 23455
    Prev
    Next
    INDEX
    Explanations

    the word "que" in various contexts, indicating its focus on questioning or emphasizing

    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
     itſelf
    -1.15
     auffi
    -1.09
     Chriſt
    -1.02
     myſelf
    -1.02
     Jefus
    -1.00
     himſelf
    -1.00
     ſeveral
    -0.95
    ſelf
    -0.95
     contextLoads
    -0.94
    jména
    -0.92
    POSITIVE LOGITS
     que
    1.30
    Que
    1.16
     Que
    1.16
     QUE
    1.00
     that
    0.88
    que
    0.87
     że
    0.84
     they
    0.82
    that
    0.81
     we
    0.81
    Activations Density 0.009%

    No Known Activations