© 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. 14581
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "class" in various contexts

    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
    })));
    -0.79
    Peny
    -0.76
    ніципалі
    -0.75
    rateful
    -0.74
     uſed
    -0.73
    eryllium
    -0.72
    devším
    -0.71
     neceffary
    -0.71
    tritte
    -0.71
    edicated
    -0.71
    POSITIVE LOGITS
     class
    3.25
     Class
    2.95
    class
    2.79
     CLASS
    2.69
    Class
    2.65
     classes
    2.62
    CLASS
    2.31
     Classes
    2.30
     classe
    2.24
     clase
    2.16
    Activations Density 0.080%

    No Known Activations