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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 1429
    Prev
    Next
    INDEX
    Explanations

    mentions of "game" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -1.05
     متعلقه
    -0.81
    PerformLayout
    -0.80
    )}]{
    -0.80
    middels
    -0.79
     bezeich
    -0.78
    ostante
    -0.77
    Награды
    -0.76
    Literatuur
    -0.76
    otonin
    -0.76
    POSITIVE LOGITS
     games
    1.55
    games
    1.36
     Games
    1.28
     Game
    1.27
     game
    1.27
    game
    1.22
    Games
    1.17
     GAME
    1.15
    Game
    1.14
     GAMES
    1.13
    Activations Density 0.037%

    No Known Activations