© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 40
    Prev
    Next
    INDEX
    Explanations

    concepts related to luck and fortune

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    luck or being lucky

    np_acts-logits-general · gemini-2.0-flash

    lucky streaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     kaynağından
    -0.72
    PostExecute
    -0.66
    EFIAPI
    -0.61
     préoccup
    -0.53
    <_>
    -0.53
    riwal
    -0.52
     intersti
    -0.52
     ioutil
    -0.51
     Bellow
    -0.50
     Krim
    -0.48
    POSITIVE LOGITS
     luck
    3.18
     lucky
    3.01
     LUCK
    2.67
    lucky
    2.53
     fortunate
    2.51
     Luck
    2.48
    luck
    2.43
    Lucky
    2.38
     Lucky
    2.33
    Luck
    2.31
    Activations Density 0.329%

    No Known Activations