© 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. 14918
    Prev
    Next
    INDEX
    Explanations

    titles and references in texts

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

    Text within quotation marks

    np_acts-logits-general · gemini-2.0-flash

    start of titles or topics

    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
    tvguidetime
    -0.90
    ंदीखरीदारी
    -0.88
     typelib
    -0.78
     Wikimedijinoj
    -0.75
    存于互联网档案馆
    -0.74
    styleType
    -0.73
     Egli
    -0.73
     AssemblyCulture
    -0.73
    ViewFeatures
    -0.72
    MIDDLEWARE
    -0.71
    POSITIVE LOGITS
     The
    1.09
     Making
    0.95
    Making
    0.92
     the
    0.92
     making
    0.90
     What
    0.89
     getting
    0.86
     a
    0.85
     Getting
    0.85
    The
    0.84
    Activations Density 0.169%

    No Known Activations