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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53176
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific components related to biochemistry and molecular biology

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

    scientific and technical terms

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ingly
    -0.85
    ruptcy
    -0.81
     SND
    -0.81
     Magdalen
    -0.79
     Jop
    -0.79
     McFadden
    -0.78
     halle
    -0.75
    izophrenia
    -0.74
     päivä
    -0.73
     Wendell
    -0.72
    POSITIVE LOGITS
     Jacobson
    0.87
    Gemma
    0.69
     Hein
    0.68
     Hadd
    0.66
     Roma
    0.65
    ︎
    0.65
    évaluateur
    0.65
     Tew
    0.64
     Faw
    0.64
    Rost
    0.63
    Activations Density 0.647%

    No Known Activations