© 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. 3066
    Prev
    Next
    INDEX
    Explanations

    indications of research findings and their implications or significance in scientific studies

    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
    
    -0.84
     متعلقه
    -0.81
     &___
    -0.77
    évaluateur
    -0.74
    出版年
    -0.74
    UnusedPrivate
    -0.72
     beginnetje
    -0.71
     bezeichneter
    -0.70
    :✨
    -0.69
    GraphicsUnit
    -0.69
    POSITIVE LOGITS
     been
    0.90
     since
    0.82
     lately
    0.68
     recently
    0.68
     NSCoder
    0.66
     recentemente
    0.65
     recent
    0.61
     gotten
    0.59
    been
    0.59
     sejak
    0.58
    Activations Density 1.012%

    No Known Activations