© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 981
    Prev
    Next
    INDEX
    Explanations

    references to women's employment rights and related legal provisions

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

    legal terminology and details related to employment law, specifically around the Family and Medical Leave Act (FMLA).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     صد
    -0.35
     integridad
    -0.33
    vaient
    -0.32
    量
    -0.32
     pengurus
    -0.31
     contents
    -0.31
    capabilities
    -0.31
    Contents
    -0.31
     obsah
    -0.30
     Ehre
    -0.30
    POSITIVE LOGITS
     holidays
    0.70
     informée
    0.67
     Holidays
    0.62
    holidays
    0.61
    ंदीखरीदारी
    0.61
     vacations
    0.57
    ftagPool
    0.56
    Holidays
    0.54
    noons
    0.54
     sick
    0.54
    Activations Density 0.113%

    No Known Activations