© 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. 1099
    Prev
    Next
    INDEX
    Explanations

    conditional structures and logical operations in programming

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

    Code, identifiers, and file paths

    np_acts-logits-general · gemini-2.0-flash

    abbreviations and technical terms

    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
    <bos>
    -0.63
     nakalista
    -0.56
    出版年
    -0.54
     Мексичка
    -0.49
    jfree
    -0.47
     Italijanski
    -0.46
    Palmar
    -0.46
     Sélectionnez
    -0.45
    thren
    -0.44
    月号
    -0.43
    POSITIVE LOGITS
    AnchorStyles
    1.12
    WebVitals
    1.01
    BagConstraints
    1.00
    queryInterface
    0.93
    bootstrapcdn
    0.90
    AndEndTag
    0.90
    MethodManager
    0.89
     utafitiHapana
    0.85
    uxxxx
    0.84
     وتسجيلات
    0.83
    Activations Density 3.759%

    No Known Activations