© 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. 20-GEMMASCOPE-RES-16K
    11. 7641
    Prev
    Next
    INDEX
    Explanations

    comment syntax and documentation formatting in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.97
    
    -0.94
    RegressionTest
    -0.88
    fromnode
    -0.87
    setVerticalGroup
    -0.83
     SwitchCompat
    -0.82
    tvguidetime
    -0.82
     queſta
    -0.82
    ViewImports
    -0.81
    featureID
    -0.80
    POSITIVE LOGITS
    ///
    0.73
     the
    0.66
    //
    0.65
    *
    0.51
    The
    0.51
    /*
    0.50
     *
    0.48
    #
    0.48
     The
    0.47
     
    0.47
    Activations Density 0.022%

    No Known Activations