© 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. 8366
    Prev
    Next
    INDEX
    Explanations

    terms related to being "bare" and ethnicity

    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
     Mandate
    -0.58
     luy
    -0.57
     deten
    -0.55
     Halter
    -0.55
     चीज़ों
    -0.54
     Milton
    -0.54
     oran
    -0.53
     Gadgets
    -0.53
    KeySpec
    -0.51
     congre
    -0.50
    POSITIVE LOGITS
     bare
    0.91
     AssemblyCulture
    0.73
    bare
    0.73
    Bare
    0.71
     bear
    0.71
     Kro
    0.68
    Personendaten
    0.68
    matology
    0.66
     Bare
    0.65
    belea
    0.64
    Activations Density 0.069%

    No Known Activations