© 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. 24-GEMMASCOPE-RES-16K
    11. 8760
    Prev
    Next
    INDEX
    Explanations

    references to astronomical features and comparisons to natural formations

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

    stars and planets

    np_acts-logits-general · gemini-2.0-flash

    planets and stars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.63
     مشين
    -0.63
    sizeCache
    -0.56
    Бахар
    -0.55
    shund
    -0.54
    setVerticalGroup
    -0.52
     समीक्षक
    -0.52
     createStore
    -0.50
    (!__
    -0.48
    RenderAtEndOf
    -0.48
    POSITIVE LOGITS
     planets
    1.63
     planet
    1.40
     astronomers
    1.37
     Planets
    1.36
     galaxy
    1.35
     celestial
    1.32
     astronomy
    1.31
     galaxies
    1.31
     stars
    1.31
     interstellar
    1.30
    Activations Density 0.531%

    No Known Activations