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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9498
    Prev
    Next
    INDEX
    Explanations

    terms related to sanctions and their impact in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteLiteral
    -0.55
    autogui
    -0.54
    safety
    -0.50
    ajevo
    -0.49
    quam
    -0.49
    ceum
    -0.49
    UTERS
    -0.49
    roek
    -0.49
    plash
    -0.49
     Обра
    -0.48
    POSITIVE LOGITS
     droughts
    0.85
     drought
    0.78
     trophic
    0.71
    المناصب
    0.70
     kasarigan
    0.70
     sanctions
    0.69
     Monfieur
    0.65
     Drought
    0.65
    webElementGuid
    0.62
    expandindo
    0.61
    Activations Density 0.909%

    No Known Activations