© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1375
    Prev
    Next
    INDEX
    Explanations

    financial terms related to currency and counterfeiting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    othelioma
    -0.59
    帖最后由
    -0.58
    TagMode
    -0.57
    tagHelperRunner
    -0.56
    ∎
    -0.54
    AddTagHelper
    -0.50
     كومونز
    -0.49
     الرياضيه
    -0.48
    uite
    -0.48
    AnchorTagHelper
    -0.48
    POSITIVE LOGITS
     coins
    0.77
     money
    0.73
     currency
    0.70
     banknotes
    0.66
     monedas
    0.66
     coin
    0.66
     Coins
    0.65
     moneda
    0.65
     Currency
    0.65
    money
    0.65
    Activations Density 0.278%

    No Known Activations