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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 8616
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and payments

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

    The token "payment"

    np_acts-logits-general · gemini-2.0-flash

    payment or movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ed
    -1.10
    a
    -0.91
    i
    -0.76
    солю
    -0.72
    ا
    -0.71
    ності
    -0.69
    er
    -0.68
    ever
    -0.64
    ities
    -0.64
    ika
    -0.63
    POSITIVE LOGITS
    atement
    0.64
     daim
    0.64
    tant
    0.63
    EMENT
    0.63
    EMENTS
    0.61
    Laurence
    0.59
     sement
    0.59
    /
    
    0.59
     Acton
    0.57
    nue
    0.57
    Activations Density 0.225%

    No Known Activations