© 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. 31-GEMMASCOPE-RES-131K
    6. 84380
    Prev
    Next
    INDEX
    Explanations

    references to medical history and previous cases

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

    medical and family history

    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
     history
    -1.62
    history
    -1.50
    History
    -1.43
     History
    -1.39
     HISTORY
    -1.38
    HISTORY
    -1.32
     histories
    -1.24
     sejarah
    -1.05
     geschiedenis
    -1.03
    历史
    -1.02
    POSITIVE LOGITS
     nahilalakip
    0.42
    RTLU
    0.40
     rich
    0.38
     Públicas
    0.36
     roleId
    0.35
     Könige
    0.34
     roomId
    0.34
     návr
    0.34
    stuk
    0.34
     lengkap
    0.34
    Activations Density 0.032%

    No Known Activations