Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2666
    Prev
    Next
    INDEX
    Explanations

    terms related to banking and financial transactions, specifically deposits and withdrawals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neurial
    -0.70
     Wür
    -0.66
    Ordinal
    -0.62
     racc
    -0.59
    selas
    -0.58
    ICAL
    -0.58
    Weblinks
    -0.58
     Kier
    -0.57
    chaine
    -0.56
     програм
    -0.56
    POSITIVE LOGITS
     deposit
    2.42
     Deposit
    2.28
     deposits
    2.23
     DEPOSIT
    2.15
    deposit
    2.15
     Deposits
    2.12
    Deposit
    2.06
    Deposits
    1.96
     deposited
    1.94
     depositing
    1.88
    Activations Density 0.098%

    No Known Activations