© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 393
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms and references related to analysis and evaluations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contextLoads
    -0.47
    InjectAttribute
    -0.44
     HttpNotFound
    -0.44
     виправивши
    -0.42
     ErrIntOverflow
    -0.42
    Tembelea
    -0.42
    TacToe
    -0.41
    انجليز
    -0.41
    لاعات
    -0.41
    retudo
    -0.41
    POSITIVE LOGITS
     Genehmigung
    0.44
    /**
    0.44
    (!__
    0.40
    coltà
    0.37
     UPS
    0.36
    BERS
    0.36
     Alden
    0.35
    veras
    0.35
    ційний
    0.35
    Приятного
    0.34
    Activations Density 0.884%

    No Known Activations