© 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. 12883
    Prev
    Next
    INDEX
    Explanations

    references to lottery winnings and related stories

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

    References to lotteries, gambling, and jackpots, often mentioning specific games (Powerball, Mega Millions) or amounts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @juliussteen
    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
    قایناق‌لار
    -0.40
    AnchorStyles
    -0.39
    Дереккөздер
    -0.38
     invokingState
    -0.38
    zboi
    -0.36
     صوتيه
    -0.35
    NotBlank
    -0.34
     Iliad
    -0.32
    ModelMap
    -0.32
     useHistory
    -0.32
    POSITIVE LOGITS
     lottery
    0.75
     Lottery
    0.70
    lottery
    0.65
    Lottery
    0.61
    teries
    0.58
     winnings
    0.50
     المعيارى
    0.49
     tonight
    0.49
     winning
    0.49
    lucky
    0.48
    Activations Density 0.036%

    No Known Activations