© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 8855
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or official actions and proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.51
    исленность
    -0.50
    AndroidJUnit
    -0.48
    >({
    -0.47
    참고
    -0.47
    一見
    -0.45
     Almost
    -0.45
    Almost
    -0.45
     nearly
    -0.44
     Inscrivez
    -0.44
    POSITIVE LOGITS
     perhaps
    1.00
     maybe
    0.93
     somehow
    0.92
    perhaps
    0.85
     alguna
    0.81
     Perhaps
    0.79
     algún
    0.78
    Perhaps
    0.77
     possibly
    0.76
     kanske
    0.73
    Activations Density 0.990%

    No Known Activations