© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15281
    Prev
    Next
    INDEX
    Explanations

    beginning phrases or sections in a narrative

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

    Followed by "Q" or related to vaccines

    np_acts-logits-general · gemini-2.0-flash

    COVID vaccine discussions

    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
     termites
    -0.56
     jaren
    -0.56
     éve
    -0.55
    Years
    -0.54
    curities
    -0.54
     anual
    -0.54
    創業
    -0.53
     years
    -0.52
     convencional
    -0.52
    Rüyada
    -0.51
    POSITIVE LOGITS
     vaccine
    0.97
     COVID
    0.96
     vaccination
    0.93
     Omicron
    0.91
     vaccinated
    0.91
     unvaccinated
    0.91
     epidemio
    0.89
     Vaccination
    0.87
     omicron
    0.85
     Covid
    0.85
    Activations Density 0.097%

    No Known Activations