© 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. 8-GEMMASCOPE-RES-16K
    11. 10706
    Prev
    Next
    INDEX
    Explanations

    negations and contrasting expressions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !*\
    -0.66
     SearchView
    -0.48
    iastes
    -0.47
    Bioaccumulative
    -0.44
    篇
    -0.43
    piac
    -0.43
     endif
    -0.43
    luci
    -0.43
    WEBPACK
    -0.43
     riten
    -0.42
    POSITIVE LOGITS
     חיצוניים
    0.85
    kháu
    0.75
     Instead
    0.72
     instead
    0.71
    而非
    0.69
     बजाय
    0.68
    あくまで
    0.68
    SharedDtor
    0.68
     propOrder
    0.67
    而不是
    0.67
    Activations Density 0.245%

    No Known Activations