© 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. 10259
    Prev
    Next
    INDEX
    Explanations

    HTML tags related to stylesheets and links to CSS files

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

    HTML stylesheet links

    np_acts-logits-general · gemini-2.0-flash

    linking stylesheets

    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
     estekak
    -0.47
    Slf
    -0.46
    SALUD
    -0.43
     виправивши
    -0.43
     itemprop
    -0.43
     ویکی‌پدیا
    -0.43
    GUARD
    -0.43
    ohan
    -0.43
    PlayerPrefs
    -0.43
    casila
    -0.42
    POSITIVE LOGITS
    stylesheet
    2.58
    httphttps
    0.71
    interopRequire
    0.63
    AutoSize
    0.58
    ReusableCell
    0.56
     BorderSide
    0.55
    __(/*!
    0.54
     initComponents
    0.53
    printStackTrace
    0.52
    IBOutlet
    0.48
    Activations Density 0.021%

    No Known Activations