© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13100
    Prev
    Next
    INDEX
    Explanations

    phrases related to entrepreneurship and business ownership

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

    Preceding tokens of businesses and websites

    np_acts-logits-general · gemini-2.0-flash

    own business operation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     dramatist
    -0.49
     officials
    -0.49
    Scientist
    -0.48
     sfeer
    -0.47
    íslu
    -0.46
     Sciento
    -0.45
     dentists
    -0.45
     chercheurs
    -0.45
     funcionarios
    -0.45
     sociologists
    -0.44
    POSITIVE LOGITS
     business
    1.19
     negócio
    1.04
     businesses
    1.00
     verksamhet
    0.99
     bisnis
    0.98
     operation
    0.98
     negocio
    0.96
     enterprise
    0.93
    business
    0.93
     бизнеса
    0.89
    Activations Density 0.275%

    No Known Activations