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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2433
    Prev
    Next
    INDEX
    Explanations

    instances of promotions or raises in employment contexts

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

    Tokens related to career advancement/promotion

    np_acts-logits-general · gemini-2.0-flash

    promoted opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reportWebVitals
    -0.56
    الحياه
    -0.53
     collectons
    -0.47
    MongoClient
    -0.47
    getWriter
    -0.46
     createState
    -0.45
    IContainer
    -0.44
     smtplib
    -0.44
     drying
    -0.43
     <",
    -0.43
    POSITIVE LOGITS
     promotion
    2.61
     promotions
    2.35
     Promotion
    2.25
     promoted
    2.22
    promotion
    2.16
    Promotion
    2.10
     Promotions
    1.97
    promoted
    1.90
    promo
    1.86
    Promotions
    1.85
    Activations Density 0.279%

    No Known Activations