© 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. 28-GEMMASCOPE-RES-16K
    11. 8039
    Prev
    Next
    INDEX
    Explanations

    references to golf-related activities and equipment

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

    golf

    np_acts-logits-general · gemini-2.0-flash

    golf and golf-related activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inuti
    -0.41
     فريبيس
    -0.40
     échelle
    -0.39
     cumplido
    -0.38
     vole
    -0.37
    ckeye
    -0.37
    AndEndTag
    -0.36
    баты
    -0.36
    PRNewswire
    -0.36
    celana
    -0.36
    POSITIVE LOGITS
     golf
    1.34
     golfers
    1.28
    Golf
    1.24
     golfer
    1.21
     golfing
    1.20
    golf
    1.20
     Golf
    1.20
     GOLF
    1.05
    ⛳
    1.03
    GOLF
    1.00
    Activations Density 0.040%

    No Known Activations