© 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. 33-GEMMASCOPE-RES-16K
    6. 7343
    Prev
    Next
    INDEX
    Explanations

    references to competitive gaming or gameplay features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bienes
    -0.36
     Comissão
    -0.36
    ftagPool
    -0.35
     paneles
    -0.32
     hadas
    -0.30
    WebElementEntity
    -0.30
     colgante
    -0.30
    ffekt
    -0.30
    meiras
    -0.29
    Dele
    -0.28
    POSITIVE LOGITS
     matchmaking
    0.99
     Ranked
    0.90
     multiplayer
    0.89
     ranked
    0.87
     match
    0.85
     lobbies
    0.85
     matches
    0.84
    ranked
    0.79
     Match
    0.79
    Ranked
    0.79
    Activations Density 0.116%

    No Known Activations