© 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. 0-GEMMASCOPE-RES-16K
    6. 10380
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities, particularly when discussing relationships or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.57
     Grüsse
    -0.54
     Wikiseite
    -0.51
     tiefe
    -0.51
     löyty
    -0.48
     içerisinde
    -0.47
     asegur
    -0.47
     שוליים
    -0.46
     jelasnya
    -0.45
     facilidad
    -0.45
    POSITIVE LOGITS
     Symptom
    0.67
     symptom
    0.66
     bell
    0.63
     Modern
    0.61
     Houſe
    0.60
     Simulation
    0.59
     eng
    0.58
    Modern
    0.57
    modern
    0.57
     cron
    0.56
    Activations Density 0.258%

    No Known Activations