© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 1059
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "matrix" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noqa
    -0.84
    LookAnd
    -0.78
    сылкі
    -0.70
    ushka
    -0.70
    seeable
    -0.69
     Roskov
    -0.68
     Conscience
    -0.68
     Yann
    -0.67
    Tight
    -0.65
     zw
    -0.65
    POSITIVE LOGITS
     StatefulWidget
    0.82
     BoxDecoration
    0.81
    matrices
    0.77
    eit
    0.70
     Matrix
    0.68
    autoconfigure
    0.65
     Bress
    0.65
     Matrices
    0.64
     MATRIX
    0.64
     Lait
    0.64
    Activations Density 0.189%

    No Known Activations