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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8521
    Prev
    Next
    INDEX
    Explanations

    elements related to measurements, distinctions, or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     everywhere
    -0.79
     itſelf
    -0.79
    everywhere
    -0.73
    ſelf
    -0.72
     ſome
    -0.69
    ſelves
    -0.69
     fometimes
    -0.66
     ordf
    -0.66
     purpoſe
    -0.65
     Everywhere
    -0.64
    POSITIVE LOGITS
     apiece
    0.82
     nakalista
    0.75
    Kaynakça
    0.69
    ImageContext
    0.66
    分別
    0.65
    SharedCtor
    0.64
    分别
    0.61
     namely
    0.61
    basicConfig
    0.60
     подряд
    0.60
    Activations Density 0.638%

    No Known Activations