© 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. 4450
    Prev
    Next
    INDEX
    Explanations

    references to health conditions and therapeutic practices

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

    before figures, notes, or websites

    np_acts-logits-general · gemini-2.0-flash

    photos and visual content

    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
    TagMode
    -0.80
    ContentAsync
    -0.73
    AndEndTag
    -0.70
    afficheront
    -0.64
     autorytatywna
    -0.62
    styleType
    -0.61
     EconPapers
    -0.60
     ziua
    -0.60
     resourceCulture
    -0.60
    IntoConstraints
    -0.59
    POSITIVE LOGITS
     photos
    0.98
     photographs
    0.93
     illustrations
    0.86
     interviews
    0.85
     diagrams
    0.83
     pictures
    0.81
    photos
    0.76
     glossary
    0.76
     charts
    0.76
     photo
    0.75
    Activations Density 0.496%

    No Known Activations