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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10704
    Prev
    Next
    INDEX
    Explanations

    terms related to betting and gambling

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

    starting with "bet" or containing "β"

    np_acts-logits-general · gemini-2.0-flash

    bet or beta variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     general
    -0.51
    unately
    -0.50
     circular
    -0.49
    mousse
    -0.49
    otá
    -0.49
     fu
    -0.47
    korb
    -0.47
    WindowConstants
    -0.47
     término
    -0.46
    います
    -0.45
    POSITIVE LOGITS
     BET
    1.02
    RegressionTest
    1.00
     bets
    0.93
     bet
    0.90
    bet
    0.88
    Bet
    0.87
     Betten
    0.86
     Bets
    0.86
     bett
    0.86
    Bets
    0.84
    Activations Density 0.115%

    No Known Activations