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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 7260
    Prev
    Next
    INDEX
    Explanations

    terms related to monetary amounts and financial calculations

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

    monetary amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alfombra
    -0.52
     ventaja
    -0.50
     Saúde
    -0.48
     cumplido
    -0.47
     accès
    -0.47
    pantalones
    -0.46
     ventana
    -0.46
     Jehová
    -0.46
     Economía
    -0.45
     parha
    -0.45
    POSITIVE LOGITS
     money
    1.05
    money
    0.84
     amount
    0.83
     amounts
    0.82
     Money
    0.81
    Money
    0.77
     Amount
    0.73
     monies
    0.71
    金额
    0.71
     cash
    0.71
    Activations Density 0.179%

    No Known Activations