© 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. 5659
    Prev
    Next
    INDEX
    Explanations

    elements and keywords related to programming, particularly in Java and related technologies

    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
     marta
    -0.63
     CreateTagHelper
    -0.56
     fabia
    -0.55
     ᾿
    -0.52
    كتشاف
    -0.52
    rès
    -0.52
    awakeFromNib
    -0.52
     الرياضيه
    -0.51
    pira
    -0.51
    HideFlags
    -0.51
    POSITIVE LOGITS
     ब्रेकडाउन
    0.54
    principalColumn
    0.43
     ajudá
    0.42
     pérd
    0.36
    󠁢
    0.35
     prét
    0.34
     Infór
    0.34
     estadounid
    0.34
     Naciones
    0.33
     мәкал
    0.33
    Activations Density 1.778%

    No Known Activations