© 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. 27-GEMMASCOPE-RES-16K
    11. 12605
    Prev
    Next
    INDEX
    Explanations

    elements related to personalized advice and individual circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ыгана
    -0.56
     $_(
    -0.54
    versies
    -0.52
    rubin
    -0.52
    ModelAdmin
    -0.52
    WebElementEntity
    -0.50
     Menace
    -0.49
    FieldNumber
    -0.49
     queſta
    -0.49
    brum
    -0.48
    POSITIVE LOGITS
     situation
    1.05
     circumstances
    1.03
     situatie
    0.98
     situations
    0.94
     unique
    0.93
    situation
    0.87
     situasi
    0.85
     specific
    0.85
    情况
    0.83
     situação
    0.83
    Activations Density 0.646%

    No Known Activations