© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3631
    Prev
    Next
    INDEX
    Explanations

    references to women with the title "Mrs."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setters
    -0.74
    calibur
    -0.66
     Goy
    -0.66
     Quij
    -0.64
     Talbot
    -0.63
    erview
    -0.62
    شهاد
    -0.62
     CPT
    -0.62
    ҽ
    -0.60
     nacionais
    -0.59
    POSITIVE LOGITS
     MRS
    1.09
     Mrs
    0.95
    MRS
    0.95
    Mrs
    0.89
     mrs
    0.88
     Reine
    0.81
    Personendaten
    0.81
     prisonniers
    0.75
     LDS
    0.72
    dames
    0.72
    Activations Density 0.038%

    No Known Activations