© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 6397
    Prev
    Next
    INDEX
    Explanations

    references to medical professionals, specifically "Dr" and variations on the title

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plain
    -0.32
    ret
    -0.31
    rou
    -0.31
     These
    -0.31
     especially
    -0.30
     und
    -0.30
     pare
    -0.30
    ful
    -0.30
     particularly
    -0.29
     Non
    -0.29
    POSITIVE LOGITS
     Seuss
    0.66
    Autoritní
    0.64
    elemField
    0.64
     queſta
    0.62
     للمعارف
    0.61
    Dr
    0.61
     surla
    0.60
    SharedDtor
    0.60
    ViewImports
    0.60
     Drs
    0.60
    Activations Density 0.169%

    No Known Activations