© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14468
    Prev
    Next
    INDEX
    Explanations

    references to programming components and requirements

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

    Follows "should," "is," or a German verb

    np_acts-logits-general · gemini-2.0-flash

    should be or is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     createSlice
    -0.40
     gevolg
    -0.40
     praktijk
    -0.32
     currentValue
    -0.30
     suivi
    -0.29
    $_['
    -0.29
    lawayo
    -0.29
     CURIAM
    -0.28
     confiança
    -0.28
    riente
    -0.28
    POSITIVE LOGITS
     NSCoder
    0.57
    tagHelperRunner
    0.56
     please
    0.54
    ⅘
    0.54
    MigrationBuilder
    0.54
     Taktlose
    0.52
     Exacts
    0.51
    :✨
    0.51
    Попис
    0.51
     vaiz
    0.51
    Activations Density 1.029%

    No Known Activations