© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 1071
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to contracts and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mathcal
    -0.39
    ส
    -0.35
     bulundu
    -0.32
    ko
    -0.31
    ún
    -0.31
    Bài
    -0.30
    CA
    -0.30
     les
    -0.30
    度
    -0.30
    TryGetValue
    -0.29
    POSITIVE LOGITS
    การ
    0.77
     việc
    0.75
    RegressionTest
    0.74
    TypedDataSet
    0.71
     sự
    0.71
    Personensuche
    0.71
     חיצוניים
    0.67
     Administrativna
    0.65
    SequentialGroup
    0.65
    sự
    0.62
    Activations Density 1.031%

    No Known Activations