© 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. 38-GEMMASCOPE-RES-16K
    11. 12986
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and control flow structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.79
    RectangleBorder
    -0.70
    InputBorder
    -0.67
    enderror
    -0.65
     snippetHide
    -0.63
     يتيمه
    -0.63
     itſelf
    -0.63
    IsContent
    -0.62
    NameInMap
    -0.62
    ▬▬▬▬▬▬▬▬
    -0.59
    POSITIVE LOGITS
     /*
    0.50
     muß
    0.38
    faßt
    0.38
     Daß
    0.37
     idéia
    0.36
      
    0.35
    ↵↵
    0.35
     \#
    0.34
     goto
    0.33
     daß
    0.33
    Activations Density 0.489%

    No Known Activations