© 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. 3-GEMMASCOPE-RES-16K
    11. 3110
    Prev
    Next
    INDEX
    Explanations

    mentions of supplementary or additional information

    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
     Мексичка
    -0.56
    ⓧ
    -0.52
    setVerticalGroup
    -0.49
    IsPostBack
    -0.47
     lexer
    -0.46
     userSchema
    -0.46
     getRule
    -0.46
    HostException
    -0.45
     lendemain
    -0.45
    ImageContext
    -0.44
    POSITIVE LOGITS
     additional
    3.95
    additional
    3.56
     Additional
    3.42
    Additional
    3.39
     ADDITIONAL
    2.94
    ADDITIONAL
    2.75
     zusätzlichen
    2.58
     zusätzliche
    2.55
     adicionales
    2.55
     adicional
    2.55
    Activations Density 0.091%

    No Known Activations