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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 7999
    Prev
    Next
    INDEX
    Explanations

    keywords specifically related to golf and its associated equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.67
     الحره
    -0.57
     culturelles
    -0.57
    JTextArea
    -0.56
    CopyWith
    -0.56
    йлер
    -0.56
    texts
    -0.56
    Composable
    -0.55
     pinulongan
    -0.55
    granate
    -0.55
    POSITIVE LOGITS
     golf
    1.35
     golfer
    1.27
    Golf
    1.20
     golfers
    1.19
     Golf
    1.19
     golfing
    1.18
    golf
    1.16
     GOLF
    1.04
    GOLF
    0.96
    ⛳
    0.83
    Activations Density 0.038%

    No Known Activations