© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 1128
    Prev
    Next
    INDEX
    Explanations

    terms related to articles or documents and their identifiers

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

    article or articles

    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
    conserv
    -0.55
    owatt
    -0.55
     Lockwood
    -0.53
    Здравствуйте
    -0.52
    umbing
    -0.52
     Roskov
    -0.51
    myspace
    -0.51
    stalgia
    -0.50
    Loves
    -0.50
    showConfirm
    -0.50
    POSITIVE LOGITS
     article
    1.23
     Article
    1.18
    Article
    1.09
    article
    1.07
     ARTICLE
    0.94
     articles
    0.91
     Articles
    0.85
     Artikel
    0.81
    ARTICLE
    0.81
     artículo
    0.78
    Activations Density 0.012%

    No Known Activations