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. 20-GEMMASCOPE-RES-16K
    6. 10318
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions and related activities

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

    Monetary transfers and transactions

    np_acts-logits-general · gemini-2.0-flash

    money transfer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Попис
    -0.77
     '\\;'
    -0.75
     Drapeau
    -0.72
    tagHelperRunner
    -0.72
     utafitiHapana
    -0.70
    GEBURTSDATUM
    -0.70
    oredCriteria
    -0.70
     Allociné
    -0.69
     GreatSchools
    -0.67
    ="@+
    -0.66
    POSITIVE LOGITS
     transfer
    1.42
     transfers
    1.33
     Transfer
    1.29
    transfer
    1.22
     Transfers
    1.18
    Transfer
    1.16
     transferring
    1.16
    transfers
    1.10
     transaction
    1.09
     TRANSFER
    1.08
    Activations Density 0.177%

    No Known Activations