© 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. 7602
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to finite and abstract algebraic structures

    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
     فريبيس
    -0.80
    WebElementEntity
    -0.72
    iſen
    -0.72
    ſelves
    -0.69
     समीक्षाओं
    -0.68
    guiente
    -0.66
     förslag
    -0.66
     laſſen
    -0.66
    IntoConstraints
    -0.65
     MainAxisSize
    -0.65
    POSITIVE LOGITS
    {
    0.73
    s
    0.65
    <b>
    0.50
    <strong>
    0.50
    ic
    0.50
    {~
    0.49
    IC
    0.45
    a
    0.44
    C
    0.44
    co
    0.43
    Activations Density 0.119%

    No Known Activations