© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3887
    Prev
    Next
    INDEX
    Explanations

    the concept of "wholeness" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    DJANGO
    -0.65
     nakalista
    -0.65
     hairdryer
    -0.62
    riezmann
    -0.62
    ICIAN
    -0.62
     sonnet
    -0.62
    aarrggbb
    -0.61
     DataTypes
    -0.60
     Scully
    -0.60
     neutrinos
    -0.60
    POSITIVE LOGITS
     whole
    3.26
    whole
    3.15
    Whole
    3.07
     Whole
    2.91
     WHOLE
    2.79
     entire
    2.33
     Entire
    1.89
     ganze
    1.87
    Entire
    1.80
    entire
    1.79
    Activations Density 0.049%

    No Known Activations