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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 5130
    Prev
    Next
    INDEX
    Explanations

    references to laboratory techniques and assays used in biological research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addContainerGap
    -0.52
    ומית
    -0.49
    disambiguation
    -0.47
    arvi
    -0.43
    rø
    -0.42
    ARTER
    -0.42
    arana
    -0.42
     ngại
    -0.41
    bonucle
    -0.41
    amili
    -0.40
    POSITIVE LOGITS
     according
    3.47
    according
    2.93
     According
    2.70
    According
    2.70
     selon
    2.46
     según
    2.38
     ACCORD
    2.30
     accordance
    2.24
     volgens
    2.23
     enligt
    2.14
    Activations Density 0.625%

    No Known Activations