© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12558
    Prev
    Next
    INDEX
    Explanations

    references to statistical metrics and percentages in data analysis

    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
    期刊论文
    -0.39
    Autoritní
    -0.39
    homonymie
    -0.38
    Lähteet
    -0.36
    stuk
    -0.35
    StoryboardSegue
    -0.35
     길
    -0.35
    Pico
    -0.34
     للاسماء
    -0.34
    autorité
    -0.34
    POSITIVE LOGITS
     percentage
    1.09
    percentage
    1.03
     percent
    0.98
     Percentage
    0.98
     percentages
    0.96
     porcentaje
    0.94
    Percentage
    0.93
     (%)
    0.90
    percent
    0.90
    PERCENT
    0.90
    Activations Density 1.630%

    No Known Activations