Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13128
    Prev
    Next
    INDEX
    Explanations

    references to employment and unemployment issues

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

    joblessness

    np_acts-logits-general · gemini-2.0-flash

    employment and unemployment rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     صوتيه
    -0.50
    DMETHOD
    -0.38
    creativecommons
    -0.37
    transQ
    -0.36
     Barros
    -0.35
     aDecoder
    -0.35
    TProtocol
    -0.35
     تضيفلها
    -0.35
    rest
    -0.34
    EXTERN
    -0.34
    POSITIVE LOGITS
     unemployment
    1.01
     employment
    0.95
     Unemployment
    0.94
     Employment
    0.93
    employment
    0.90
     unemployed
    0.88
    Employment
    0.87
     jobless
    0.84
    Unemployment
    0.83
     desemple
    0.81
    Activations Density 0.178%

    No Known Activations