© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5215
    Prev
    Next
    INDEX
    Explanations

    patterns related to code annotations and decorators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]))
    -0.87
    mybatisplus
    -0.84
    Personendaten
    -0.82
     ―――――
    -0.82
    EndInit
    -0.80
     resultCode
    -0.78
    StoryboardSegue
    -0.75
     ་་
    -0.75
    ³)
    -0.74
    
    -0.73
    POSITIVE LOGITS
     @
    1.70
     '@
    1.50
    @
    1.45
    >@
    1.44
    (@
    1.40
    ('@
    1.40
    ("@
    1.40
    .@
    1.38
    :@
    1.35
     "@
    1.35
    Activations Density 0.272%

    No Known Activations