© 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. 18-GEMMASCOPE-RES-16K
    11. 3250
    Prev
    Next
    INDEX
    Explanations

    structured numerical data or values with specific formatting

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

    after abbreviations or special characters

    np_acts-logits-general · gemini-2.0-flash

    ELF prefix/labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     OBL
    -0.81
     
    -0.80
     препратки
    -0.79
     Goss
    -0.77
    RequestMapping
    -0.74
    öffentlich
    -0.74
     CIT
    -0.73
    WARR
    -0.72
    Demografia
    -0.71
     Lorenz
    -0.71
    POSITIVE LOGITS
      
    0.98
    RenderAtEndOf
    0.96
    :✨
    0.81
     Wikispecies
    0.78
     Myles
    0.73
     Alves
    0.71
    paraíso
    0.71
    CodedInputStream
    0.69
    y
    0.67
     SEDS
    0.66
    Activations Density 0.268%

    No Known Activations