© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 6755
    Prev
    Next
    INDEX
    Explanations

    repeated or significant punctuation and formatting elements in a document

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

    academic subjects and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -1.07
    ViewImports
    -0.95
    Personendaten
    -0.91
     GenerationType
    -0.90
     defaultstate
    -0.88
    principalColumn
    -0.85
    WithIOException
    -0.84
    Географиясе
    -0.82
    setVerticalGroup
    -0.80
    Personensuche
    -0.80
    POSITIVE LOGITS
     chemistry
    0.60
     chemical
    0.50
     chemin
    0.50
     Chemistry
    0.45
     molecular
    0.42
     pharmacology
    0.39
     teaching
    0.39
     science
    0.39
     education
    0.37
     Islam
    0.36
    Activations Density 0.001%

    No Known Activations