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. 3-GEMMASCOPE-RES-16K
    6. 11166
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and references related to chemistry and environmental science

    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
    ing
    -0.79
     McRae
    -0.71
     Brodie
    -0.71
     Hama
    -0.69
    ING
    -0.67
     métro
    -0.67
     Deer
    -0.67
    lugin
    -0.66
    Hama
    -0.66
     Mil
    -0.66
    POSITIVE LOGITS
     Amon
    0.97
    AccessorTable
    0.95
    Paraguay
    0.93
     Heisenberg
    0.92
    Zeneca
    0.88
     Paraguay
    0.87
     Tallinn
    0.87
     Thebes
    0.86
     Indoch
    0.85
     Efq
    0.84
    Activations Density 1.902%

    No Known Activations