© 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. 310
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" in the text

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

    conjunctions indicating relationships and connecting ideas

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

    lists conjunctions

    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
    ItemBackground
    -0.53
    Cyfeiriadau
    -0.52
    Посилання
    -0.51
     theirs
    -0.51
    enumi
    -0.49
    zzá
    -0.48
     Schuster
    -0.47
    andy
    -0.47
    meden
    -0.47
    elf
    -0.47
    POSITIVE LOGITS
     lastly
    1.41
     finally
    1.33
     generally
    1.29
     overall
    1.22
     ultimately
    1.16
    reszcie
    1.15
    generally
    1.12
    何より
    1.10
    overall
    1.09
     наконец
    1.09
    Activations Density 0.118%

    No Known Activations