© 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. 23-GEMMASCOPE-RES-16K
    11. 6562
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lumpur
    -0.30
    锈钢
    -0.29
     bulundu
    -0.28
    
    -0.27
     aziende
    -0.26
    vänt
    -0.25
    ViewImports
    -0.25
     CLOSE
    -0.24
    บุ
    -0.24
    Насе
    -0.24
    POSITIVE LOGITS
    featureID
    0.76
     typelib
    0.68
    onOptions
    0.66
    httphttps
    0.65
     defaultstate
    0.64
    argout
    0.64
     EconPapers
    0.61
    RenderAtEndOf
    0.61
     disambiguazione
    0.60
    Especially
    0.60
    Activations Density 0.357%

    No Known Activations