© 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. 24-GEMMASCOPE-RES-16K
    11. 5806
    Prev
    Next
    INDEX
    Explanations

    references to gender and sexual orientation, particularly related to boys and girls

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

    "Boy" or "Scout" appearing in text

    np_acts-logits-general · gemini-2.0-flash

    boy scouts or boy wizard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.93
    ThroughAttribute
    -0.92
     doInBackground
    -0.66
    transQ
    -0.66
    setCellValue
    -0.64
     uVar
    -0.64
    WebControls
    -0.61
    
    -0.61
    dafx
    -0.59
    expandindo
    -0.59
    POSITIVE LOGITS
     scout
    0.83
     scouts
    0.80
    FRIEND
    0.76
     Scout
    0.71
    friends
    0.71
    friend
    0.71
     Scouts
    0.69
    couts
    0.63
    scout
    0.61
    Friend
    0.57
    Activations Density 0.073%

    No Known Activations