© 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. 9-GEMMASCOPE-RES-16K
    11. 14264
    Prev
    Next
    INDEX
    Explanations

    emotional interactions and expressions among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     législation
    -0.52
     otomatig
    -0.49
     EconPapers
    -0.48
     Offisielt
    -0.48
     Вікіпе
    -0.47
    BagConstraints
    -0.46
     logistique
    -0.46
     specification
    -0.45
     laboral
    -0.43
     razonable
    -0.43
    POSITIVE LOGITS
     oprot
    0.51
     astore
    0.45
     choked
    0.42
     shook
    0.42
     dripping
    0.41
     crouched
    0.40
    ChildScrollView
    0.40
    findpost
    0.40
     smiled
    0.40
    afficheront
    0.40
    Activations Density 0.227%

    No Known Activations