Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 11772
    Prev
    Next
    INDEX
    Explanations

    mentions of female characters referred to as "Mrs."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulkner
    -0.80
    ToLeft
    -0.79
    appliquer
    -0.77
    setters
    -0.74
     Calib
    -0.73
     समीक्षक
    -0.72
     Avalon
    -0.70
    ukone
    -0.70
    riwal
    -0.70
     Goy
    -0.70
    POSITIVE LOGITS
     Mrs
    1.30
     MRS
    1.28
    Mrs
    1.22
     mrs
    1.20
    MRS
    1.11
    mrs
    0.96
    dames
    0.83
    Dr
    0.74
    GraphicsUnit
    0.72
     Dr
    0.70
    Activations Density 0.024%

    No Known Activations