© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 12678
    Prev
    Next
    INDEX
    Explanations

    terms related to business concepts and practices

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

    business

    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
     sereia
    -0.48
    retudo
    -0.48
     Itália
    -0.48
    Hopefully
    -0.46
    hopefully
    -0.46
     sobretudo
    -0.45
     toalha
    -0.45
     almofada
    -0.45
     hopefully
    -0.44
     kohta
    -0.44
    POSITIVE LOGITS
    usiness
    1.21
     business
    1.12
    business
    1.11
     Business
    1.11
    Business
    1.10
     BUSINESS
    1.04
    BUSINESS
    1.02
     Businesses
    0.82
     businesses
    0.77
    biz
    0.74
    Activations Density 0.020%

    No Known Activations