© 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. 23-GEMMASCOPE-RES-16K
    11. 14216
    Prev
    Next
    INDEX
    Explanations

    elements related to function definitions and method calls in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.85
     Efq
    -1.80
     themſelves
    -1.77
     himſelf
    -1.72
     becauſe
    -1.71
     Monfieur
    -1.70
     itſelf
    -1.68
     Jefus
    -1.67
     Theſe
    -1.66
     whoſe
    -1.63
    POSITIVE LOGITS
    <unused63>
    0.77
    <unused61>
    0.71
    <unused62>
    0.69
    <unused60>
    0.64
    ‍
    0.33
    ­
    0.33
    enumi
    0.29
    ‌
    0.28
    ‏
    0.28
    <eos>
    0.27
    Activations Density 1.484%

    No Known Activations