© 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. 21-GEMMASCOPE-RES-16K
    11. 13701
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical structures and formats, particularly arrays and matrices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endblock
    -0.52
    ⓘ
    -0.50
    ing
    -0.43
     nakalista
    -0.42
    pageNumber
    -0.41
    iecie
    -0.41
    UnitTesting
    -0.40
    Cyfeiriadau
    -0.40
    <eos>
    -0.39
     viewDidLoad
    -0.39
    POSITIVE LOGITS
    <table>
    0.79
    <thead>
    0.75
     '{@
    0.73
    ParallelGroup
    0.69
    findpost
    0.69
    tabular
    0.68
    richTextPanel
    0.67
    mtable
    0.67
    FromArgb
    0.66
    Datuak
    0.64
    Activations Density 0.125%

    No Known Activations