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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 8223
    Prev
    Next
    INDEX
    Explanations

    the concept of "whole" or "entire" as it relates to completeness or entirety 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 @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     totaal
    -0.55
     creș
    -0.53
     fièvre
    -0.52
     massima
    -0.48
     모두
    -0.48
    oriques
    -0.47
    Viki
    -0.47
     celui
    -0.46
     nào
    -0.46
     Ohren
    -0.45
    POSITIVE LOGITS
     lotta
    1.06
    hearted
    1.02
     lot
    0.91
     gamut
    0.91
    BeginInit
    0.89
     thing
    0.86
     entire
    0.82
    heartedly
    0.81
     bunch
    0.74
    meal
    0.74
    Activations Density 0.060%

    No Known Activations