Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 87044
    Prev
    Next
    INDEX
    Explanations

    terms related to golf and golfing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    a
    -0.46
    etas
    -0.45
     viewType
    -0.44
     Mina
    -0.43
     תא
    -0.43
     initState
    -0.43
     Mea
    -0.43
    A
    -0.42
     veroor
    -0.42
    *~*~
    -0.42
    POSITIVE LOGITS
    Golf
    1.20
    golf
    1.17
     GOLF
    1.16
     golf
    1.14
     Golf
    1.13
     golfing
    1.03
    GOLF
    1.00
     golfers
    0.82
    ゴルフ
    0.78
    ⛳
    0.77
    Activations Density 0.002%

    No Known Activations