© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 16304
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and syntax used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.30
    initWith
    -0.30
     Artículos
    -0.29
    eller
    -0.29
     tø
    -0.29
     sprzed
    -0.29
     المرجع
    -0.29
    buttonBar
    -0.28
     Independencia
    -0.28
     перево
    -0.28
    POSITIVE LOGITS
    math
    1.32
    displaystyle
    0.95
    存于互联网档案馆
    0.78
     kaarangay
    0.72
    Personendaten
    0.71
    SourceChecksum
    0.68
     @"/
    0.67
    adaptiveStyles
    0.63
     kasarigan
    0.62
    httphttps
    0.62
    Activations Density 0.317%

    No Known Activations