© 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. 14805
    Prev
    Next
    INDEX
    Explanations

    sentences that express observations or factual statements

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

    arguments and debates

    np_acts-logits-general · gemini-2.5-flash-lite

    sentence-initial content words (words that begin a new sentence or discourse turn, like "There", "If", "It", "I", "This").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    bootstrapcdn
    -0.63
    WebVitals
    -0.61
    DotNetBar
    -0.59
    
    -0.59
    queryInterface
    -0.59
    OrNil
    -0.59
     estekak
    -0.58
    出版年
    -0.57
    下载附件
    -0.57
    featureID
    -0.56
    POSITIVE LOGITS
     arguments
    0.36
    arguments
    0.33
    Arguments
    0.32
     discussione
    0.30
     inderdaad
    0.29
     debated
    0.29
     realtà
    0.28
     argument
    0.28
    <bos>
    0.28
     neither
    0.28
    Activations Density 0.012%

    No Known Activations