© 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. 34-GEMMASCOPE-RES-16K
    11. 3145
    Prev
    Next
    INDEX
    Explanations

    points related to ongoing development and improvement in processes or projects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    exitRule
    -0.43
     actionMode
    -0.40
     responsabilité
    -0.35
     gén
    -0.35
     compétence
    -0.34
    diakan
    -0.34
     iniciativa
    -0.34
    ebabkan
    -0.34
     tâche
    -0.34
     bandoulière
    -0.33
    POSITIVE LOGITS
     refine
    1.77
     refinement
    1.71
     refinements
    1.66
     refining
    1.65
     refined
    1.56
     fine
    1.40
     perfecting
    1.38
    refined
    1.34
    refine
    1.30
     Refin
    1.25
    Activations Density 0.556%

    No Known Activations