© 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. 5376
    Prev
    Next
    INDEX
    Explanations

    statistics and performance metrics related to sports players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    statistical sports performance numbers (like points, rebounds, yards, etc.).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     protoimpl
    -0.54
    transQ
    -0.50
    hauer
    -0.45
    ſammen
    -0.44
     overwhelmingly
    -0.44
    soever
    -0.44
    cerer
    -0.43
    testens
    -0.43
     незавершена
    -0.43
     fundamentally
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.59
    ClientSize
    0.57
     AssemblyTitle
    0.50
    évaluateur
    0.44
     itemprop
    0.37
    ніципалі
    0.36
     nakalista
    0.36
    Scénario
    0.35
    glo
    0.34
    degree
    0.34
    Activations Density 0.060%

    No Known Activations