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. 24-GEMMASCOPE-RES-16K
    6. 14019
    Prev
    Next
    INDEX
    Explanations

    financial transactions or discussions involving costs, payments, and investments

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

    currency (rupees, profit, cash, price)

    np_acts-logits-general · gemini-2.0-flash

    money and financial terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    newswire
    -0.57
     BoxDecoration
    -0.54
     Diretto
    -0.52
    ViewFeatures
    -0.52
    الدراسه
    -0.51
     Charlemagne
    -0.49
    mphony
    -0.49
     Euphrates
    -0.48
    ReusableCell
    -0.48
     sauvage
    -0.47
    POSITIVE LOGITS
     Rs
    0.92
    Rs
    0.75
     ₹
    0.70
     Ru
    0.69
    ₹
    0.67
     rs
    0.64
    Ru
    0.61
     sanctioned
    0.60
    AndEndTag
    0.59
     rupees
    0.58
    Activations Density 0.092%

    No Known Activations