© 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. 3450
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions indicating relationships and connections between ideas

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

    Prepositions in Romance languages

    np_acts-logits-general · gemini-2.0-flash

    pronouns in Spanish, French, Portuguese

    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
    NameInMap
    -1.00
    SourceChecksum
    -0.78
    PerformLayout
    -0.76
    はじめに
    -0.74
     actionMode
    -0.74
     also
    -0.74
     Majefty
    -0.73
     Cæsar
    -0.73
     onely
    -0.71
    also
    -0.68
    POSITIVE LOGITS
     них
    0.67
     него
    0.54
     elle
    0.54
     ellos
    0.53
     ell
    0.51
     elles
    0.51
     un
    0.50
     él
    0.49
     eux
    0.48
     una
    0.46
    Activations Density 0.044%

    No Known Activations