© 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. 9064
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and variable assignments in expressions

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

    preceding capitalized words

    np_acts-logits-general · gemini-2.0-flash

    names of people, places, and organizations

    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
    ArgsConstructor
    -0.96
     NDEBUG
    -0.80
    ViewImports
    -0.80
    Personendaten
    -0.78
     AppModule
    -0.74
    الحياه
    -0.73
    ConstraintMaker
    -0.72
     BrowserModule
    -0.69
    `;
    -0.69
     useAppContext
    -0.68
    POSITIVE LOGITS
     الدولى
    0.68
    </h1>
    0.56
    setVerticalGroup
    0.55
    fortawesome
    0.48
     …
    0.48
    .*")]
    0.48
    >>>>>>>
    0.47
    </strong>
    0.46
    fsch
    0.46
    prnewswire
    0.43
    Activations Density 8.439%

    No Known Activations