© 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. 3-GEMMASCOPE-RES-16K
    11. 14413
    Prev
    Next
    INDEX
    Explanations

    references to the "Mad Men" television series and its related elements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     propOrder
    -1.07
    InjectAttribute
    -0.96
    Portail
    -0.88
     кӀ
    -0.86
    IUrlHelper
    -0.83
    astéroïdes
    -0.80
     layui
    -0.79
     Silt
    -0.78
    .*")]
    -0.78
    __).
    -0.78
    POSITIVE LOGITS
     Mad
    3.47
    Mad
    3.34
     mad
    3.28
     MAD
    2.71
    mad
    2.69
    MAD
    2.47
     Maddox
    1.54
     madd
    1.42
     Madd
    1.41
     madness
    1.40
    Activations Density 0.108%

    No Known Activations