© 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. 34-GEMMASCOPE-RES-16K
    11. 10728
    Prev
    Next
    INDEX
    Explanations

    occurrences of Java-related classes and interfaces, especially from the javax package

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Isaacs
    -0.49
     Cardoso
    -0.48
    HasIndex
    -0.45
     Tapia
    -0.41
     Persson
    -0.41
     Vitale
    -0.41
     Schulte
    -0.41
     Scherer
    -0.40
     Olsson
    -0.39
     Pozna
    -0.38
    POSITIVE LOGITS
    swing
    0.91
     swing
    0.74
     Swing
    0.66
    findpost
    0.66
    IntoConstraints
    0.58
    Swing
    0.54
     swings
    0.54
     FontWeight
    0.52
    énario
    0.52
     GenerationType
    0.52
    Activations Density 0.014%

    No Known Activations