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. 16-GEMMASCOPE-RES-16K
    6. 6370
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal documents and references to regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "and"

    np_acts-logits-general · gemini-2.0-flash

    listing items separated by commas and and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mrc
    -0.59
     استنادى
    -0.59
     appunto
    -0.58
     Kitts
    -0.57
    MADRID
    -0.56
     courseId
    -0.55
    apollo
    -0.54
     sonore
    -0.54
     Dink
    -0.54
     bookId
    -0.53
    POSITIVE LOGITS
     and
    0.74
     וכן
    0.73
     the
    0.71
     valamint
    0.70
     plus
    0.67
     sowie
    0.65
     그리고
    0.65
     للاسماء
    0.65
    以及
    0.64
     sekä
    0.61
    Activations Density 0.298%

    No Known Activations