© 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. 116899
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and summations within formal text

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

    sum ranges over

    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
     Мексичка
    -0.37
    viewDidLoad
    -0.36
    rrggbb
    -0.35
    InjectAttribute
    -0.35
    ffic
    -0.34
     disappointing
    -0.33
    Complete
    -0.32
     ddelweddau
    -0.32
    Matchers
    -0.31
    __(/*!
    -0.31
    POSITIVE LOGITS
    RenderAtEndOf
    0.58
     autorytatywna
    0.55
    ientôt
    0.49
    XmlAccessType
    0.49
     Einfluß
    0.48
    alitions
    0.47
     influence
    0.45
     MenuView
    0.44
    XmlAccessorType
    0.43
     nakalista
    0.43
    Activations Density 0.412%

    No Known Activations