© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6021
    Prev
    Next
    INDEX
    Explanations

    keywords related to important concepts or entities

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

    "The [adjective] [noun]"

    np_acts-logits-general · gemini-2.0-flash

    key or main aspects

    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
    ExtendWith
    -0.82
     kasarigan
    -0.69
    KommentareTeilen
    -0.68
    AxisAlignment
    -0.64
    gorithm
    -0.61
    хьтан
    -0.61
    Rhestr
    -0.61
     समीक्षक
    -0.61
     Normdatei
    -0.60
    TargetException
    -0.59
    POSITIVE LOGITS
     key
    1.32
     main
    1.29
     primary
    1.17
     cornerstone
    1.17
     central
    1.15
     major
    1.15
     centerpiece
    1.11
     principale
    1.10
    main
    1.07
     core
    1.05
    Activations Density 0.320%

    No Known Activations