© 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. 3436
    Prev
    Next
    INDEX
    Explanations

    the letters "T" at the beginning of sentences or phrases

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

    Token "T" followed by lowercase letters

    np_acts-logits-general · gemini-2.0-flash

    texts starting with T

    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
    Datuak
    -0.55
     moks
    -0.52
    om
    -0.50
     merci
    -0.47
     官方
    -0.46
     deep
    -0.45
    Gweler
    -0.45
    er
    -0.45
     finally
    -0.44
     local
    -0.44
    POSITIVE LOGITS
    parsedMessage
    0.71
     jScrollPane
    0.68
     oprot
    0.64
    findpost
    0.63
     initComponents
    0.62
    sizeCache
    0.59
    RetentionPolicy
    0.58
    glie
    0.57
    modelBuilder
    0.57
     testator
    0.56
    Activations Density 0.206%

    No Known Activations