© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4349
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or brands, particularly those associated with music or popular culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting with "Bru", "Ru", or "subrufescens"

    np_acts-logits-general · gemini-2.0-flash

    Bru or ru followed by endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reaſon
    -0.60
    NTB
    -0.59
     Sabina
    -0.58
     Segurança
    -0.58
     Achtung
    -0.58
     pleaſure
    -0.57
     Epilepsy
    -0.57
    phant
    -0.55
     Cina
    -0.55
     Heiden
    -0.54
    POSITIVE LOGITS
    ru
    0.85
    Bru
    0.83
     Bru
    0.80
     Ru
    0.77
     ru
    0.69
     bru
    0.67
    bru
    0.61
    Ru
    0.61
     Bruce
    0.57
    Brus
    0.56
    Activations Density 0.176%

    No Known Activations