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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13171
    Prev
    Next
    INDEX
    Explanations

    references to specific games and gaming experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Бележки
    -0.43
    InstrumentedTest
    -0.42
     świad
    -0.41
     שוליים
    -0.41
    jsxFileName
    -0.39
     Nationen
    -0.38
    styleType
    -0.38
     gyhoeddwyd
    -0.37
     voegen
    -0.37
    ไลน์
    -0.37
    POSITIVE LOGITS
     game
    0.88
     Game
    0.76
     games
    0.72
    game
    0.68
     GAME
    0.67
    Game
    0.67
     Games
    0.64
     puzzle
    0.62
    GAME
    0.62
     puzzles
    0.61
    Activations Density 0.140%

    No Known Activations