© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8922
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming imports and package declarations

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

    Code imports and technical abbreviations

    np_acts-logits-general · gemini-2.0-flash

    import statements

    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
    dafx
    -0.65
    expandindo
    -0.65
    ViewFeatures
    -0.63
     awakeFromNib
    -0.62
    ########.
    -0.61
    IUrlHelper
    -0.61
    MLLoader
    -0.60
    setVerticalGroup
    -0.57
    TextInputLayout
    -0.56
     Administrativna
    -0.56
    POSITIVE LOGITS
    import
    0.38
     caixas
    0.38
     taglio
    0.36
     aikana
    0.35
     olev
    0.35
     ninguém
    0.35
     botas
    0.34
     muchacho
    0.34
     lançamento
    0.34
     viajeros
    0.34
    Activations Density 0.017%

    No Known Activations