© 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. 5-GEMMASCOPE-RES-16K
    11. 13521
    Prev
    Next
    INDEX
    Explanations

    terms and vocabulary related to programming and data structures, particularly in the context of Python and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.66
     ་་
    -1.48
     myſelf
    -1.45
     ―――――
    -1.38
     iſt
    -1.38
     Theſe
    -1.38
    ſelf
    -1.31
     faſt
    -1.29
     Monfieur
    -1.27
     Houſe
    -1.25
    POSITIVE LOGITS
     Z
    0.92
     Ra
    0.90
     Er
    0.90
     Qu
    0.89
     Ma
    0.86
     Ar
    0.85
     Ba
    0.85
     Ke
    0.84
     K
    0.83
     Al
    0.82
    Activations Density 8.546%

    No Known Activations