© 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. 37-GEMMASCOPE-RES-16K
    11. 5155
    Prev
    Next
    INDEX
    Explanations

    Java programming syntax, especially related to object instance checks and method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PostInfinity
    -0.54
    GEBURTSDATUM
    -0.51
     utafitiHapana
    -0.51
    makeConstraints
    -0.50
     Himo
    -0.45
    込
    -0.44
     strang
    -0.44
    +#+
    -0.43
     strings
    -0.42
     viewDidLoad
    -0.41
    POSITIVE LOGITS
    float
    0.94
    double
    0.83
     float
    0.82
    char
    0.79
     double
    0.76
     char
    0.75
    int
    0.65
     int
    0.62
    byte
    0.61
    boolean
    0.60
    Activations Density 0.227%

    No Known Activations