© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 108254
    Prev
    Next
    INDEX
    Explanations

    references to the character "Lucky" and related descriptors indicating luck or fortune

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lucky
    -1.91
    Lucky
    -1.80
     lucky
    -1.54
    lucky
    -1.38
     LUCK
    -1.20
     fortunate
    -1.06
    LUCK
    -1.02
    幸运
    -0.89
     Luck
    -0.88
     unlucky
    -0.83
    POSITIVE LOGITS
     queſta
    0.60
    BindView
    0.54
     surla
    0.53
     ſta
    0.52
     myſelf
    0.48
    respect
    0.48
     fubject
    0.48
    bewerken
    0.47
     vectorstock
    0.47
    ۢ
    0.47
    Activations Density 0.002%

    No Known Activations