© 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. 28-GEMMASCOPE-RES-16K
    11. 2824
    Prev
    Next
    INDEX
    Explanations

    references to relationships and family connections within a narrative context

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

    Mentions "woman," "women," or female individuals

    np_acts-logits-general · gemini-2.0-flash

    woman, wife, sister

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     męski
    -0.82
     himself
    -0.81
    的他
    -0.79
    himself
    -0.74
     muž
    -0.72
     manly
    -0.71
     męskie
    -0.71
     manhood
    -0.71
    ‍♂️
    -0.70
     sám
    -0.68
    POSITIVE LOGITS
     woman
    0.91
     lady
    0.87
     herself
    0.86
     businesswoman
    0.85
     women
    0.85
     girl
    0.85
     womanhood
    0.84
    woman
    0.82
     female
    0.81
     Woman
    0.81
    Activations Density 1.507%

    No Known Activations