© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15889
    Prev
    Next
    INDEX
    Explanations

    information related to golf and its associated elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     golf
    -0.57
     Golf
    -0.50
     saites
    -0.46
    Golf
    -0.45
    golf
    -0.44
     GOLF
    -0.44
    ゴルフ
    -0.44
     externi
    -0.42
     tỏi
    -0.40
    endaft
    -0.40
    POSITIVE LOGITS
     bunkers
    0.63
     bunker
    0.62
    featureID
    0.61
     Bunk
    0.57
    +#+#
    0.57
    ViewFeatures
    0.55
    URLException
    0.54
    WithIOException
    0.54
     par
    0.51
     approach
    0.49
    Activations Density 0.113%

    No Known Activations