© 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. 16-GEMMASCOPE-RES-16K
    6. 4072
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and corruption

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

    money or compensation

    np_acts-logits-general · gemini-2.0-flash

    money, proceeds, refunds, dividends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IMPORTED
    -0.53
    Manbalar
    -0.50
    Precios
    -0.47
    êtes
    -0.46
     мет
    -0.42
    ály
    -0.41
    貫
    -0.41
     intensity
    -0.41
    плу
    -0.40
    iços
    -0.40
    POSITIVE LOGITS
     money
    1.09
     denaro
    0.96
     monies
    0.95
     cash
    0.89
    money
    0.83
     funds
    0.83
     dinheiro
    0.80
     dinero
    0.78
     moneys
    0.78
     amounts
    0.78
    Activations Density 0.448%

    No Known Activations