© 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. 13137
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and function definitions

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

    Code, symbols, or uncommon punctuation

    np_acts-logits-general · gemini-2.0-flash

    SON, vortices, operate

    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
    ValueStyle
    -0.49
    Dichloropropene
    -0.39
     BitSet
    -0.39
    olem
    -0.39
    Begriffsklä
    -0.39
     "','
    -0.38
    </em>
    -0.38
    isi
    -0.36
     mi
    -0.35
     censiti
    -0.33
    POSITIVE LOGITS
    MigrationBuilder
    1.25
    RegressionTest
    1.10
     ویکی‌پدیا
    0.94
     ddelweddau
    0.91
    CloseOperation
    0.87
    KURZBESCHREIBUNG
    0.84
     HttpNotFound
    0.83
     ویکی‌پدیای
    0.83
     AttributeSet
    0.82
    __':
    0.81
    Activations Density 2.765%

    No Known Activations