© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128593
    Prev
    Next
    INDEX
    Explanations

    code-related terms, particularly focusing on import statements in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     américains
    -0.37
     condições
    -0.37
     micrófono
    -0.36
     problemer
    -0.36
     jurado
    -0.36
     precisión
    -0.35
     profundidad
    -0.35
     erfaring
    -0.35
     planificación
    -0.35
     tatuajes
    -0.35
    POSITIVE LOGITS
    stateProvider
    0.81
    onViewCreated
    0.76
     defaultstate
    0.74
    ExtendWith
    0.69
    AppCompat
    0.68
     surla
    0.68
     StatefulWidget
    0.65
    setVerticalGroup
    0.65
     JpaRepository
    0.62
    viewDidLoad
    0.61
    Activations Density 0.001%

    No Known Activations