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

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 13706
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, particularly in Java and React Native contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otheby
    -0.46
     Persson
    -0.40
     Backman
    -0.39
    новременно
    -0.39
    DataPropertyName
    -0.39
     Olsson
    -0.38
     chip
    -0.37
     tez
    -0.37
     still
    -0.36
     CONSEQU
    -0.36
    POSITIVE LOGITS
    SequentialGroup
    0.88
    MessageTagHelper
    0.83
     estekak
    0.73
     kasarigan
    0.68
    RegressionTest
    0.66
    SharedCtor
    0.65
    StoryboardSegue
    0.65
     viewDidLoad
    0.64
    featureID
    0.64
    Diweddarwch
    0.63
    Activations Density 0.267%

    No Known Activations