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

    Neuronpedia

    Jacobian LensNEW
    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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 55230
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to medical and scientific contexts, particularly those describing conditions and processes

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

    associated with or requiring conditions

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    aarrggbb
    -0.38
    うえ
    -0.37
    geving
    -0.36
    <thead>
    -0.34
    wijl
    -0.33
    הערות
    -0.33
    buck
    -0.33
     however
    -0.32
    andReturn
    -0.32
    SafeMath
    -0.32
    POSITIVE LOGITS
     ویکی‌پدی
    0.77
     autorytatywna
    0.72
    NameInMap
    0.64
     resourceCulture
    0.59
     незавершена
    0.56
    qrstuvwxyz
    0.56
     OFDb
    0.51
    Aholisi
    0.49
    Билгалдахарш
    0.47
     للاسماء
    0.47
    Activations Density 0.060%

    No Known Activations