© 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. 33-GEMMASCOPE-RES-16K
    11. 9620
    Prev
    Next
    INDEX
    Explanations

    terms related to sports involvement and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.66
     invokingState
    -0.58
    HasAnnotation
    -0.46
     ujednoznacz
    -0.45
     referrerpolicy
    -0.44
    saraba
    -0.44
    prefixer
    -0.43
    
    -0.43
    ineno
    -0.42
    IVEREF
    -0.40
    POSITIVE LOGITS
     sports
    1.91
     sport
    1.78
     athletes
    1.70
     Sports
    1.66
    Sports
    1.63
    sports
    1.63
     athlete
    1.61
     sporting
    1.61
     athletic
    1.60
     football
    1.55
    Activations Density 0.653%

    No Known Activations