© 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
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9396
    Prev
    Next
    INDEX
    Explanations

    references to diseases or medical conditions mentioned alongside quantitative data or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.73
    featureID
    -0.68
    flashdata
    -0.65
    IsPostBack
    -0.63
    WithIOException
    -0.61
    AccessorTable
    -0.58
    Ecotoxicity
    -0.58
    
    -0.56
    __':
    
    -0.56
     Infórmanos
    -0.56
    POSITIVE LOGITS
     Winfrey
    0.43
    合衆
    0.43
    otechnology
    0.39
     רבה
    0.38
    floxacin
    0.36
    hdysval
    0.36
     eksp
    0.36
     Serikat
    0.36
    webElement
    0.35
    potamus
    0.35
    Activations Density 2.024%

    No Known Activations