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. 3-GEMMASCOPE-RES-16K
    6. 12475
    Prev
    Next
    INDEX
    Explanations

    the word "namely" and its variations, indicating a focus on specifying or detailing examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —
    -0.65
     ști
    -0.64
    كومة
    -0.64
     sewa
    -0.61
     συμ
    -0.61
     Quig
    -0.60
     pubblici
    -0.60
     Sewell
    -0.59
     Woj
    -0.59
     McDonough
    -0.59
    POSITIVE LOGITS
     namely
    1.47
    namely
    1.39
     Namely
    1.33
     nämlich
    1.08
    
    0.95
     viz
    0.93
     nemlig
    0.93
     namelijk
    0.93
    yaitu
    0.93
    expandindo
    0.87
    Activations Density 0.057%

    No Known Activations