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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2030
    Prev
    Next
    INDEX
    Explanations

    references to global trade and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ziua
    -0.43
     urbanos
    -0.41
     oprot
    -0.40
    urn
    -0.39
    DropColumn
    -0.38
     mairie
    -0.38
     osoby
    -0.36
    onViewCreated
    -0.35
    UpInside
    -0.35
    TimePicker
    -0.35
    POSITIVE LOGITS
     WTO
    0.63
     arbitrage
    0.58
     globalization
    0.57
     trade
    0.56
     Tariff
    0.55
    Trade
    0.54
     Globalization
    0.54
     exports
    0.52
     tariff
    0.52
     liberalization
    0.51
    Activations Density 0.145%

    No Known Activations