© 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. 22-GEMMASCOPE-RES-16K
    11. 11705
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "whole" or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Whole" followed by quantity or related terms

    np_acts-logits-general · gemini-2.0-flash

    whole bunch or lot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     creș
    -0.53
     모두
    -0.53
     fièvre
    -0.52
     massima
    -0.49
    Viki
    -0.49
     nakalista
    -0.49
     totaal
    -0.47
     Liens
    -0.47
     estimat
    -0.47
    oriques
    -0.47
    POSITIVE LOGITS
     lotta
    1.05
     entire
    1.04
    hearted
    1.02
     thing
    0.95
     lot
    0.94
     whole
    0.86
    whole
    0.86
     gamut
    0.84
     ENTIRE
    0.82
    Entire
    0.81
    Activations Density 0.065%

    No Known Activations