© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 345
    Prev
    Next
    INDEX
    Explanations

    financial transactions and significant monetary values related to business deals

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

    cost and expense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     conveniently
    -0.34
     hoş
    -0.33
    föra
    -0.32
     Pros
    -0.32
    Chham
    -0.31
     Convenient
    -0.30
     hafif
    -0.30
     convenient
    -0.30
     pequena
    -0.29
     handy
    -0.29
    POSITIVE LOGITS
     pricey
    0.82
     expensive
    0.80
     costly
    0.75
     costing
    0.73
    Expensive
    0.73
     $\$
    0.72
     overpriced
    0.70
    expensive
    0.69
    WireFormatLite
    0.69
     setPrice
    0.66
    Activations Density 0.051%

    No Known Activations