© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5695
    Prev
    Next
    INDEX
    Explanations

    sequences of symbols and special characters

    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
    enumii
    -0.92
     defaultstate
    -0.88
     intptr
    -0.84
    webElementXpaths
    -0.84
     للاسماء
    -0.81
     autorytatywna
    -0.79
     Baillargeon
    -0.76
    :✨
    -0.75
    Diwedd
    -0.75
     Профиль
    -0.74
    POSITIVE LOGITS
    ambi
    0.39
    bruk
    0.38
    <em>
    0.37
     мозга
    0.37
        
    0.37
    permum
    0.37
     New
    0.36
    <strong>
    0.36
    ↵
    0.36
    writerow
    0.35
    Activations Density 0.784%

    No Known Activations