© 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. 22-GEMMASCOPE-RES-16K
    11. 114
    Prev
    Next
    INDEX
    Explanations

    instances of specific numerical or coded data and information

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Text within brackets ([], (), {})

    np_acts-logits-general · gemini-2.0-flash

    scientific papers and citations

    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
    Negative Logits
     …
    -0.49
     sort
    -0.47
     the
    -0.47
     réessayer
    -0.45
     whatever
    -0.45
     morning
    -0.45
     any
    -0.44
     after
    -0.43
    помним
    -0.43
    شوف
    -0.43
    POSITIVE LOGITS
     дописавши
    0.84
    bibitem
    0.80
    IUrlHelper
    0.79
     jScrollPane
    0.78
     preprint
    0.77
     reprinted
    0.74
     retraction
    0.73
     AUTHORS
    0.72
    Hochspringen
    0.71
    PhysRev
    0.70
    Activations Density 0.396%

    No Known Activations