© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2446
    Prev
    Next
    INDEX
    Explanations

    relationships and classifications within biological families

    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
     otomatig
    -0.57
    Suara
    -0.57
    orino
    -0.56
    ethene
    -0.55
     Walls
    -0.54
    ariste
    -0.54
    Addo
    -0.52
    localScale
    -0.52
    छे
    -0.51
     walls
    -0.50
    POSITIVE LOGITS
     category
    0.91
     CATEGORY
    0.75
     segment
    0.71
     Category
    0.68
     subdivision
    0.68
     categorie
    0.67
     catégorie
    0.67
     group
    0.66
    Kategorie
    0.65
     gruppe
    0.65
    Activations Density 1.140%

    No Known Activations