© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1772
    Prev
    Next
    INDEX
    Explanations

    references to availability or features of options or schedules

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

    math 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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    saraba
    -0.85
    Geplaatst
    -0.84
    DeleteBehavior
    -0.83
    sizeCache
    -0.75
     للاسماء
    -0.74
    PreferredItem
    -0.71
     feroit
    -0.70
    SaveVideo
    -0.70
     consultato
    -0.68
    /**
    -0.68
    POSITIVE LOGITS
    <h3>
    0.89
    <h2>
    0.83
    <h6>
    0.78
    <h4>
    0.77
    <h1>
    0.71
    <h5>
    0.64
    %%
    0.56
    NSNotification
    0.51
    jön
    0.51
    GNUC
    0.48
    Activations Density 0.002%

    No Known Activations