© 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 EvalsExportsinterp-engineNEWAPI 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. 13134
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "bye" and variations, indicating a focus on farewells or endings

    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
    %")
    -0.57
    >[]
    -0.51
     البعض
    -0.50
     Dougherty
    -0.47
     hào
    -0.47
    Искәрмәләр
    -0.47
     taget
    -0.47
     alfabe
    -0.47
    richment
    -0.47
     compagnon
    -0.47
    POSITIVE LOGITS
    BY
    1.12
     bye
    1.05
     Bye
    1.02
    By
    0.96
    bye
    0.93
    Bye
    0.88
    BYE
    0.87
     defaultstate
    0.83
     BY
    0.82
     By
    0.77
    Activations Density 0.063%

    No Known Activations