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

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 3945
    Prev
    Next
    INDEX
    Explanations

    safety and warning information related to medication and its usage

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

    Sentences containing warnings or cautions

    np_acts-logits-general · gemini-2.0-flash

    methadone, Galafold, warnings, side effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tweaked
    -0.66
     pretty
    -0.58
     tweaking
    -0.55
     arguably
    -0.54
    ponym
    -0.53
     tweaks
    -0.53
    Sadly
    -0.52
     Interestingly
    -0.51
    Interestingly
    -0.50
     Sadly
    -0.49
    POSITIVE LOGITS
     poffe
    0.77
    ſelf
    0.76
     pleaſure
    0.75
     ſtate
    0.75
     CAUTION
    0.74
     uſe
    0.74
     auffi
    0.74
     fubject
    0.74
     skall
    0.72
     enfans
    0.72
    Activations Density 0.324%

    No Known Activations