© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1606
    Prev
    Next
    INDEX
    Explanations

    mathematical comparisons and relations involving inequalities

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

    mathematical relationships involving inequalities and limits

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

    mathematical inequalities and indices

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    是一
    -0.40
    一大
    -0.39
    lio
    -0.38
     in
    -0.37
     */}
    -0.36
    JdbcTemplate
    -0.36
     a
    -0.35
    Fatalf
    -0.34
     '(
    -0.34
     (
    -0.34
    POSITIVE LOGITS
    GEBURTSDATUM
    1.16
    IUrlHelper
    1.02
     <>",
    1.00
    IntoConstraints
    0.99
     estimés
    0.97
    AsUp
    0.97
     Signalez
    0.92
     EconPapers
    0.90
    DockStyle
    0.87
    thâu
    0.85
    Activations Density 0.162%

    No Known Activations