© 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. 11-GEMMASCOPE-RES-16K
    11. 5010
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and constructs, specifically those related to type checking and object handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Commentaires
    -0.35
     extraordinario
    -0.35
     gratuites
    -0.34
     asiático
    -0.34
     État
    -0.33
     Allgemeinen
    -0.33
     état
    -0.33
     Kardinal
    -0.33
     Histórico
    -0.33
     reservado
    -0.33
    POSITIVE LOGITS
    ValueStyle
    0.78
    +#+#
    0.72
    PYX
    0.70
     Numerade
    0.68
    Vidite
    0.67
    RegressionTest
    0.66
    下载附件
    0.66
     informée
    0.63
     للمعارف
    0.63
    saraba
    0.59
    Activations Density 0.068%

    No Known Activations