© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3870
    Prev
    Next
    INDEX
    Explanations

    metaphorical expressions or idioms indicating unrealistic or overly optimistic scenarios

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

    pie

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Negative Logits
     InputDecoration
    -0.96
    ᅠ
    -0.74
    theless
    -0.70
    WithFormat
    -0.65
    rovnik
    -0.64
    Bibliograf
    -0.63
    surate
    -0.62
    thmus
    -0.61
    tiéndose
    -0.61
    paces
    -0.61
    POSITIVE LOGITS
     pies
    1.05
     Pie
    1.02
     pie
    1.00
    🥧
    0.94
    Pie
    0.90
     Pies
    0.87
    pie
    0.86
     PIE
    0.86
     crust
    0.70
     slice
    0.68
    Activations Density 0.016%

    No Known Activations