© 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. 5595
    Prev
    Next
    INDEX
    Explanations

    references to the expression of regulatory genes in cancer studies

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

    "in vivo" or "in vitro" contexts

    np_acts-logits-general · gemini-2.0-flash

    in vitro and in vivo

    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
    OCCURRED
    -0.77
    tagHelperRunner
    -0.76
    contentLoaded
    -0.76
    MLLoader
    -0.76
    IntoConstraints
    -0.75
     AssemblyProduct
    -0.74
     disambiguazione
    -0.73
    ніципалі
    -0.71
    ViewImports
    -0.71
    Personendaten
    -0.71
    POSITIVE LOGITS
     vitro
    1.02
     experimental
    0.84
     test
    0.83
     model
    0.82
     laboratory
    0.81
     human
    0.79
     vivo
    0.79
     tests
    0.77
     experiments
    0.76
     models
    0.74
    Activations Density 1.415%

    No Known Activations