© 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. 40-GEMMASCOPE-RES-16K
    11. 1937
    Prev
    Next
    INDEX
    Explanations

    statistical terms and references to data analysis methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    뀜
    -0.56
    뀐
    -0.45
     تعدى
    -0.39
    뀔
    -0.37
     Découvrez
    -0.36
    RTLR
    -0.36
     sequencing
    -0.35
    теризу
    -0.35
    anskje
    -0.34
    bottomrule
    -0.34
    POSITIVE LOGITS
     compared
    0.66
    DeleteBehavior
    0.59
    modelBuilder
    0.53
    compared
    0.53
     Compared
    0.50
     reg
    0.44
     gra
    0.44
    EndGlobalSection
    0.43
     contrasted
    0.43
    Compared
    0.43
    Activations Density 1.448%

    No Known Activations