© 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. 986
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and its impacts on behavior

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

    preceding "research" or "study"

    np_acts-logits-general · gemini-2.0-flash

    research studies

    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
    yntaxException
    -0.72
    expandindo
    -0.68
    EDEFAULT
    -0.68
    tvguidetime
    -0.68
    TypedDataSet
    -0.67
     &___
    -0.66
    醐
    -0.65
     disponibilités
    -0.64
     appelez
    -0.64
     Мексичка
    -0.63
    POSITIVE LOGITS
     studies
    2.54
     research
    2.20
    studies
    2.07
     Studies
    2.04
    Studies
    2.04
     study
    1.96
     STUDIES
    1.80
    research
    1.78
     études
    1.75
    Research
    1.75
    Activations Density 0.845%

    No Known Activations