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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13912
    Prev
    Next
    INDEX
    Explanations

    elements related to racing video games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    video games

    np_acts-logits-general · gemini-2.0-flash

    video games and gameplay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    webElementXpaths
    -0.52
     uzyska
    -0.51
     ujednoznacz
    -0.48
     resourceCulture
    -0.48
    WebServlet
    -0.47
     jspb
    -0.44
    enumii
    -0.42
     réunions
    -0.42
    DeleteBehavior
    -0.41
     للاسماء
    -0.41
    POSITIVE LOGITS
     gameplay
    0.79
     game
    0.69
     videog
    0.69
     games
    0.68
     videogame
    0.66
     Gameplay
    0.63
     multiplayer
    0.63
    gdx
    0.62
    Gameplay
    0.60
     gamers
    0.60
    Activations Density 0.147%

    No Known Activations