© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14588
    Prev
    Next
    INDEX
    Explanations

    references to sports players and their career-related details

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

    Sports player retirements or aging

    np_acts-logits-general · gemini-2.0-flash

    athlete retirement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     prefeitura
    -0.41
     calificación
    -0.36
    ลักษ
    -0.34
     houſe
    -0.34
     chargeur
    -0.34
     compreensão
    -0.33
     confusión
    -0.33
    setHorizontal
    -0.33
     personnalité
    -0.32
     kelebihan
    -0.32
    POSITIVE LOGITS
     '{@
    0.68
     retirement
    0.63
     retire
    0.62
     Retirement
    0.60
    retirement
    0.60
     Retire
    0.59
    TagMode
    0.57
    Retirement
    0.57
     retired
    0.57
     Retired
    0.56
    Activations Density 0.168%

    No Known Activations