© 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. 19-GEMMASCOPE-RES-16K
    6. 2549
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific measurements and data analysis in astrophysics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     layui
    -0.54
    IsContent
    -0.48
    cjon
    -0.47
    loem
    -0.46
     configureStore
    -0.46
    soil
    -0.45
    anium
    -0.44
     beats
    -0.44
    OrEqual
    -0.44
    stappen
    -0.43
    POSITIVE LOGITS
    :✨
    0.76
    yntaxException
    0.75
     ProtoMessage
    0.68
     Milky
    0.68
     galaxy
    0.67
     NGC
    0.67
     redshift
    0.67
    RenderAtEndOf
    0.66
     galaxies
    0.66
    NGC
    0.63
    Activations Density 1.015%

    No Known Activations