© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42554
    Prev
    Next
    INDEX
    Explanations

    specific numeric values and characters commonly used in academic references and citations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    zip codes and USA

    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
    Negative Logits
    fjspx
    -0.65
     >=",
    -0.60
     चीज़ों
    -0.60
    OGND
    -0.59
     themſelves
    -0.58
     InputDecoration
    -0.57
    𑄢
    -0.55
    曖昧さ回避
    -0.55
     BorderRadius
    -0.54
    zionalità
    -0.54
    POSITIVE LOGITS
    GOTREF
    0.46
    Décès
    0.34
     distrik
    0.31
     getAddress
    0.31
    OCCURRED
    0.28
     Tel
    0.28
    PDOException
    0.28
     endblock
    0.28
    SYSC
    0.28
     alde
    0.27
    Activations Density 0.006%

    No Known Activations