© 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 EvalsExportsinterp-engineNEWAPI 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. 16863
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structural elements in code or data definitions

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

    code and structured data

    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
    webElementGuid
    -0.84
    dafx
    -0.80
    TagMode
    -0.79
     فريبيس
    -0.78
    RenderAtEndOf
    -0.75
    存于互联网档案馆
    -0.74
    SharedCtor
    -0.74
    ReusableCell
    -0.73
     AssemblyCulture
    -0.70
     snippetHide
    -0.70
    POSITIVE LOGITS
     enfans
    0.38
     fermés
    0.37
     Púb
    0.36
     fometimes
    0.36
     Grecs
    0.35
     cherchez
    0.34
     mères
    0.34
     fiscales
    0.33
     suivants
    0.33
     chrétiens
    0.33
    Activations Density 0.020%

    No Known Activations