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. 1-GEMMASCOPE-RES-16K
    6. 13758
    Prev
    Next
    INDEX
    Explanations

    references to gaming systems and game-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    
    -0.81
     itſelf
    -0.78
    complexContent
    -0.77
    AccessorTable
    -0.77
     Theſe
    -0.76
    IUrlHelper
    -0.75
    ]")]
    -0.74
     Monfieur
    -0.74
     typelib
    -0.73
    Autoritní
    -0.73
    POSITIVE LOGITS
     Gaming
    0.85
    Gaming
    0.81
    gam
    0.81
    Gam
    0.79
    gaming
    0.79
    GAM
    0.75
     Gam
    0.70
    gamer
    0.70
    Game
    0.70
    GAME
    0.67
    Activations Density 0.059%

    No Known Activations