© 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. 144
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to development and infrastructure issues

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

    preceding industries or fields of study

    np_acts-logits-general · gemini-2.0-flash

    areas and industries

    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
     themſelves
    -0.75
     chrétiens
    -0.72
     plufieurs
    -0.70
     varandra
    -0.70
     dieux
    -0.69
     étrang
    -0.69
     zelve
    -0.69
     supérieurs
    -0.67
     himſelf
    -0.67
     gouttes
    -0.66
    POSITIVE LOGITS
     cum
    0.79
     kasarigan
    0.73
     BoxFit
    0.71
     upd
    0.67
     становника
    0.66
    AsUp
    0.63
    AndEndTag
    0.62
    cum
    0.61
     related
    0.61
    Cum
    0.56
    Activations Density 0.320%

    No Known Activations