© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3052
    Prev
    Next
    INDEX
    Explanations

    occurrences and variations of curly braces and square brackets in LaTeX code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.82
     betweenstory
    -0.81
     queſta
    -0.79
    WebElementEntity
    -0.76
     ſta
    -0.75
    webElementXpaths
    -0.74
     pleaſure
    -0.71
     Infór
    -0.71
    ſelves
    -0.70
    awtextra
    -0.70
    POSITIVE LOGITS
    usepackage
    1.09
    {
    0.63
     {
    0.50
    import
    0.48
    __(/*!
    0.47
    ::{
    0.44
    (
    0.40
    /
    0.39
    package
    0.39
     "
    0.38
    Activations Density 0.015%

    No Known Activations