© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 119981
    Prev
    Next
    INDEX
    Explanations

    significant headings or dividers in text

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

    abstract, Oxygen, In, Many, Cou, Circ, Of

    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
    parsedMessage
    -0.86
     мәкал
    -0.85
    MessageTagHelper
    -0.76
    webElementXpaths
    -0.76
    تقاوى
    -0.76
    ItemBackground
    -0.76
    ьаж
    -0.74
    SourceChecksum
    -0.74
     Numerade
    -0.74
    featureID
    -0.73
    POSITIVE LOGITS
    sus
    0.42
    :
    0.41
    kom
    0.40
    Sus
    0.40
    foo
    0.40
     cuc
    0.39
    Arguments
    0.39
    Global
    0.39
     Sus
    0.39
    Request
    0.38
    Activations Density 0.025%

    No Known Activations