© 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. 3262
    Prev
    Next
    INDEX
    Explanations

    references to medical diagnoses and symptoms

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

    PHP or Javascript code

    np_acts-logits-general · gemini-2.0-flash

    Louisiana Cajun Creole

    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
    
    -0.57
    Toronto
    -0.54
    îtra
    -0.53
    coroutines
    -0.50
     provinciale
    -0.49
     Toronto
    -0.49
    errHandler
    -0.49
     Maple
    -0.47
     Macedonian
    -0.47
    Ontario
    -0.46
    POSITIVE LOGITS
     Bayou
    0.75
     Louisiana
    0.73
    LSU
    0.72
     LSU
    0.71
     Cajun
    0.70
    Louisiana
    0.69
     Symfony
    0.66
     Baton
    0.64
     Orleans
    0.61
     Creole
    0.59
    Activations Density 0.103%

    No Known Activations