© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28526
    Prev
    Next
    INDEX
    Explanations

    references to historical inventions and their significance

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

    first occurrence

    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
     Reſ
    -1.14
     myſelf
    -1.12
     greateſt
    -1.09
     ſeveral
    -1.08
     purpoſe
    -1.05
     itſelf
    -1.05
     Theſe
    -1.05
    ſelf
    -1.02
     themſelves
    -1.01
     Diſ
    -1.00
    POSITIVE LOGITS
     really
    0.73
     truly
    0.71
     realmente
    0.69
     vraiment
    0.69
     wirklich
    0.65
     Really
    0.59
     Truly
    0.58
    Really
    0.52
    Truly
    0.51
     veramente
    0.51
    Activations Density 0.252%

    No Known Activations