© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 352
    Prev
    Next
    INDEX
    Explanations

    mentions of human rights abuses and government suppression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.78
     الرياضيه
    -0.73
     pitié
    -0.71
     Corinth
    -0.65
     שוליים
    -0.65
    IUrlHelper
    -0.61
    ództ
    -0.61
     conceding
    -0.60
     Aphrodite
    -0.60
    atoshi
    -0.59
    POSITIVE LOGITS
     persecution
    0.79
     persecu
    0.75
     perse
    0.71
     persecuted
    0.68
     arrest
    0.67
     arrests
    0.61
     persec
    0.59
     censorship
    0.56
     ban
    0.55
     arbitrary
    0.55
    Activations Density 0.313%

    No Known Activations