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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 9747
    Prev
    Next
    INDEX
    Explanations

    mentions of the compound "carbachol."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.78
     autorytatywna
    -0.71
    parsedMessage
    -0.65
    Джерела
    -0.55
     transférez
    -0.53
    клопе
    -0.53
    مصادر
    -0.52
    resizingMask
    -0.52
     otomatig
    -0.52
    Enllaces
    -0.51
    POSITIVE LOGITS
    ol
    2.99
    OL
    2.06
    Ol
    1.39
     ol
    1.32
    ols
    1.31
    olv
    1.31
     Ol
    1.23
    olni
    1.22
    olto
    1.07
    olc
    1.05
    Activations Density 0.048%

    No Known Activations