© 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. 15801
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and coding syntax

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

    Mathematical expressions with fractions

    np_acts-logits-general · gemini-2.0-flash

    x, y, z variables

    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
    yards
    -0.88
     yard
    -0.86
     yards
    -0.85
    AndroidJUnit
    -0.82
    yield
    -0.77
    yard
    -0.77
     yield
    -0.76
     Yards
    -0.75
     Yard
    -0.74
    Yard
    -0.73
    POSITIVE LOGITS
    BeginContext
    0.51
    rungsseite
    0.50
     onAnimation
    0.48
    AddHtmlAttribute
    0.48
     struct
    0.47
     gynhyrchwyd
    0.46
     فريبيس
    0.45
    struct
    0.45
     z
    0.44
    competitive
    0.44
    Activations Density 0.270%

    No Known Activations