© 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
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6530
    Prev
    Next
    INDEX
    Explanations

    locations or instances of people sitting down

    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
    fromnode
    -0.66
    RenderAtEndOf
    -0.66
    addPreferredGap
    -0.65
    InitVars
    -0.57
    Personendaten
    -0.57
    addContainerGap
    -0.56
     AssemblyVersion
    -0.55
     незавершена
    -0.55
    GEBURTSDATUM
    -0.54
    webElementXpaths
    -0.53
    POSITIVE LOGITS
     headquarters
    0.87
     Headquarters
    0.83
     HQ
    0.83
    Headquarters
    0.63
    HQ
    0.62
     hq
    0.58
    总部
    0.51
    desk
    0.50
    hq
    0.48
     desks
    0.48
    Activations Density 0.037%

    No Known Activations