© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13777
    Prev
    Next
    INDEX
    Explanations

    instructions related to the disposal of medications and safety precautions

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

    pipes and drains

    np_acts-logits-general · gemini-2.0-flash

    drainage systems and pipes

    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
    Билгалдахарш
    -0.67
    Искәрмәләр
    -0.67
    帖最后由
    -0.62
    Vidite
    -0.59
     <=",
    -0.59
    webElementXpaths
    -0.57
    numerusform
    -0.56
    ◀
    -0.56
     мәкал
    -0.56
    équences
    -0.56
    POSITIVE LOGITS
     drain
    1.38
     drains
    1.29
    drain
    1.21
     Drain
    1.18
     drainage
    1.18
     sewer
    1.15
     sewers
    1.14
     DRAIN
    1.07
    Drain
    1.04
     Drainage
    1.04
    Activations Density 0.135%

    No Known Activations