© 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. 487
    Prev
    Next
    INDEX
    Explanations

    text containing variable definitions and data types in programming contexts

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

    Capital letter followed by another capitalized letter

    np_acts-logits-general · gemini-2.0-flash

    T or Tennessee

    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
    DockStyle
    -0.69
    Autoritní
    -0.62
    SharedDtor
    -0.62
    ⓧ
    -0.61
    PerformLayout
    -0.60
    Rüyada
    -0.59
     noDo
    -0.59
    afficheront
    -0.59
    Identyfik
    -0.58
    cshtml
    -0.56
    POSITIVE LOGITS
     T
    0.85
    T
    0.84
     t
    0.69
     Thomas
    0.68
     Tennessee
    0.67
     Texas
    0.66
     TB
    0.65
    Thomas
    0.65
    Tennessee
    0.65
     т
    0.63
    Activations Density 1.818%

    No Known Activations