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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2922
    Prev
    Next
    INDEX
    Explanations

    references to casino gaming mechanics and features

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

    gambling and casino slot machine content.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aéro
    -0.39
     logistique
    -0.39
    ={({
    -0.38
     survie
    -0.38
     ragion
    -0.36
    nellement
    -0.36
    makeConstraints
    -0.36
    setVerticalGroup
    -0.36
     expéri
    -0.34
     margiela
    -0.33
    POSITIVE LOGITS
     wilds
    0.83
     scatter
    0.81
     multipliers
    0.80
     bonus
    0.79
     Scatter
    0.78
     slot
    0.77
     reels
    0.75
     Bonus
    0.75
     scat
    0.74
     multiplier
    0.71
    Activations Density 0.058%

    No Known Activations