Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13576
    Prev
    Next
    INDEX
    Explanations

    words related to names or identifiers of people, particularly those involving the name "Ay."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.62
    createServer
    -0.62
    AutoresizingMask
    -0.60
    Dichloropropene
    -0.58
    تمبر
    -0.58
    oplayer
    -0.57
     ========
    -0.57
    iour
    -0.56
    rmtree
    -0.56
     ++)
    -0.55
    POSITIVE LOGITS
     ashes
    0.56
     Мексичка
    0.53
     admixture
    0.51
     ActionBar
    0.50
    Autos
    0.50
     axles
    0.48
     adjournment
    0.48
     uncin
    0.47
    ">@
    0.46
     Aux
    0.46
    Activations Density 0.086%

    No Known Activations