© 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. 7-GEMMASCOPE-RES-16K
    11. 15737
    Prev
    Next
    INDEX
    Explanations

    Java AWT library components and related error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -1.15
    TabIndex
    -1.08
    :✨
    -0.93
    arXiv
    -0.81
     onCreate
    -0.73
    
    -0.71
    stylesheet
    -0.69
    __(/*!
    -0.67
     EconPapers
    -0.67
    msgTypes
    -0.66
    POSITIVE LOGITS
     EventArgs
    1.48
    awt
    1.09
    iostream
    1.05
    stdio
    1.03
    printStackTrace
    0.92
    pyx
    0.90
     RoutedEventArgs
    0.85
    preventDefault
    0.81
     UnityEngine
    0.79
    cstdio
    0.69
    Activations Density 0.007%

    No Known Activations