© 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. 20-GEMMASCOPE-RES-16K
    11. 1242
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding family relationships and societal dynamics

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

    males or men

    np_acts-logits-general · gemini-2.0-flash

    Hispanic men

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     madam
    -0.98
     actresses
    -0.95
     goddess
    -0.93
     actress
    -0.93
     businesswoman
    -0.93
     Actress
    -0.91
     Lady
    -0.89
     lady
    -0.89
     Mrs
    -0.87
     Madam
    -0.87
    POSITIVE LOGITS
     male
    1.28
     pria
    1.15
     masculine
    1.13
     gentlemen
    1.11
     males
    1.10
     masculino
    1.09
     boys
    1.08
     lelaki
    1.07
     manly
    1.06
     mężczy
    1.05
    Activations Density 0.706%

    No Known Activations