© 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. 4498
    Prev
    Next
    INDEX
    Explanations

    terms related to anatomical structures and medical procedures involving the heart and abdominal organs

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

    Referring to internal body spaces/cavities

    np_acts-logits-general · gemini-2.0-flash

    cavity or space

    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
    rungsseite
    -0.75
    UserScript
    -0.75
    WebVitals
    -0.68
    دانشنامهٔ
    -0.62
    Билгалдахарш
    -0.62
     oars
    -0.59
    makeConstraints
    -0.59
     nakalista
    -0.58
    metheus
    -0.57
    GEBURTSDATUM
    -0.56
    POSITIVE LOGITS
     cavity
    1.08
     hollow
    0.91
     tunnel
    0.90
     cavities
    0.87
     tunnels
    0.85
    cavity
    0.84
     space
    0.84
     chamber
    0.82
     Cavity
    0.80
     hueco
    0.75
    Activations Density 0.486%

    No Known Activations