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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3610
    Prev
    Next
    INDEX
    Explanations

    elements related to invoice processing and financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.51
    MLLoader
    -0.48
    EndProject
    -0.47
    listdir
    -0.47
    setVerticalGroup
    -0.47
    msgTypes
    -0.46
    первых
    -0.46
     Viter
    -0.45
     vertical
    -0.44
     passports
    -0.44
    POSITIVE LOGITS
     price
    1.06
    price
    1.00
     totalPrice
    1.00
     Price
    0.97
     money
    0.96
    Price
    0.95
     currency
    0.94
     dollars
    0.93
     Amount
    0.93
     Money
    0.92
    Activations Density 0.239%

    No Known Activations