© 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. 1289
    Prev
    Next
    INDEX
    Explanations

    historical facts or inventions related to feminine hygiene products, specifically tampons

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

    ancient civilizations/practices

    np_acts-logits-general · gemini-2.0-flash

    ancient civilizations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    fehl
    -0.54
    wki
    -0.49
     bạch
    -0.49
     personally
    -0.48
    abatic
    -0.46
    niak
    -0.45
     promet
    -0.45
     prome
    -0.45
    nodoc
    -0.45
    今年
    -0.44
    POSITIVE LOGITS
     earliest
    0.95
     ancient
    0.94
     древ
    0.84
    ancient
    0.84
    Ancient
    0.83
     Ancient
    0.82
     primitive
    0.81
    early
    0.81
    古代
    0.80
    Early
    0.79
    Activations Density 0.806%

    No Known Activations