© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6588
    Prev
    Next
    INDEX
    Explanations

    references to women's involvement and representation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.65
     male
    -0.56
     males
    -0.54
    URLException
    -0.53
     damski
    -0.50
     páns
    -0.49
     dámské
    -0.47
     men
    -0.46
     mâle
    -0.46
     cowok
    -0.45
    POSITIVE LOGITS
    folk
    0.85
     empowerment
    0.69
    volent
    0.56
     Empowerment
    0.52
    hood
    0.51
     suffrage
    0.49
     entrepreneurs
    0.49
     entrepreneur
    0.49
     fatale
    0.48
     mittleren
    0.48
    Activations Density 0.181%

    No Known Activations