© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 766
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and references related to species or taxonomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exécut
    -0.57
     exemplaire
    -0.55
     détru
    -0.54
     quelcon
    -0.52
     kock
    -0.52
    Viitteet
    -0.52
     exemplaires
    -0.50
    RegisterType
    -0.49
     Wurzel
    -0.49
     fär
    -0.48
    POSITIVE LOGITS
     ts
    0.91
     TS
    0.91
     Ts
    0.88
    Хьажоргаш
    0.75
    TS
    0.74
    NameInMap
    0.72
    hirts
    0.70
     wireType
    0.70
    ьаж
    0.70
    ts
    0.69
    Activations Density 0.088%

    No Known Activations