© 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-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5446
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disclaimers or limitations of responsibility related to content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TabStop
    -0.37
     quieter
    -0.35
    Wat
    -0.35
     quietly
    -0.34
     somewhat
    -0.34
     screwing
    -0.34
     fucking
    -0.33
     razu
    -0.33
    ột
    -0.33
     kemungkinan
    -0.33
    POSITIVE LOGITS
     NSCoder
    0.68
     cherchés
    0.57
     purpoſe
    0.57
    PerformLayout
    0.54
     greateſt
    0.52
    adaptiveStyles
    0.51
    VYMaps
    0.49
    ftagPool
    0.49
    ThemeOverlay
    0.49
     الحره
    0.48
    Activations Density 0.371%

    No Known Activations