© 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. 13-GEMMASCOPE-RES-16K
    11. 7069
    Prev
    Next
    INDEX
    Explanations

    quantitative measures related to fractions and percentages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uurs
    -0.40
     montagna
    -0.37
     chapter
    -0.36
    nezeu
    -0.35
     gemeente
    -0.33
     stiamo
    -0.31
     στι
    -0.30
     opge
    -0.29
     capítulo
    -0.29
    writel
    -0.29
    POSITIVE LOGITS
     Percentage
    0.92
     percentage
    0.91
    Percentage
    0.86
     percentages
    0.86
    percentage
    0.86
     (%)
    0.84
     Percent
    0.83
     porcentaje
    0.82
     percent
    0.81
    percent
    0.78
    Activations Density 1.887%

    No Known Activations