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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4804
    Prev
    Next
    INDEX
    Explanations

    terms related to trade policies and tariffs

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

    tariffs and trade

    np_acts-logits-general · gemini-2.0-flash

    tariffs on imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })();
    -0.45
     apartamentos
    -0.42
     koc
    -0.40
    CLAIMER
    -0.39
     pad
    -0.39
    obic
    -0.39
     psychi
    -0.38
     موس
    -0.37
     geha
    -0.37
    prech
    -0.37
    POSITIVE LOGITS
     trade
    1.06
     tariff
    1.06
     tariffs
    0.99
     Tariff
    0.97
     import
    0.96
     Trade
    0.93
     importing
    0.91
    expandindo
    0.90
    Trade
    0.89
    trade
    0.88
    Activations Density 0.164%

    No Known Activations