© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 13262
    Prev
    Next
    INDEX
    Explanations

    creative aspects of crafting and design in various projects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     government
    -0.35
     Constitucional
    -0.34
     hidráulica
    -0.34
     hidrá
    -0.33
    /**
    -0.31
     patrie
    -0.30
     cốt
    -0.30
     capital
    -0.30
    Experienced
    -0.30
     Houſe
    -0.30
    POSITIVE LOGITS
    IBOutlet
    0.64
     Autorizaciones
    0.61
    PreferredItem
    0.61
     surla
    0.60
     Савезне
    0.60
    Šaltiniai
    0.58
     Autorisations
    0.58
    adpleegd
    0.56
    قایناقلار
    0.56
     IBOutlet
    0.56
    Activations Density 0.509%

    No Known Activations