© 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. 11257
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight unique experiences or opportunities

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

    "A" preceding descriptive words

    np_acts-logits-general · gemini-2.0-flash

    article before descriptive adjectives

    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
    RegressionTest
    -0.61
     mxArray
    -0.59
    ItemBackground
    -0.58
     tane
    -0.54
     vân
    -0.52
    uy
    -0.51
    Descriere
    -0.50
    MigrationBuilder
    -0.50
    AutoScale
    -0.49
    __;
    -0.49
    POSITIVE LOGITS
     refreshing
    0.83
     veritable
    0.80
     remarkable
    0.77
     remarkably
    0.68
     rare
    0.68
     testament
    0.67
    refreshing
    0.66
     rafraî
    0.66
     decidedly
    0.65
     uniquely
    0.65
    Activations Density 0.294%

    No Known Activations