© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 117247
    Prev
    Next
    INDEX
    Explanations

    references to salary figures and discussions

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

    salary and wages

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ponta
    -0.52
     Ohl
    -0.48
     Watkins
    -0.47
     pick
    -0.47
    react
    -0.46
     Don
    -0.46
     Event
    -0.46
     Pent
    -0.46
    specialchars
    -0.44
     Pick
    -0.44
    POSITIVE LOGITS
     salary
    1.15
     Salary
    1.11
    Salary
    1.05
     salaries
    0.98
    salary
    0.93
     Salaries
    0.90
     salario
    0.87
     salaire
    0.82
     sueldo
    0.79
     Wages
    0.77
    Activations Density 0.004%

    No Known Activations