© 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. 21-GEMMASCOPE-RES-16K
    11. 2439
    Prev
    Next
    INDEX
    Explanations

    expressions and sentiments related to love and affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ISNI
    -0.77
    
    -0.72
     exceptionnelle
    -0.66
    Datuak
    -0.63
     altrimenti
    -0.63
     exceptionnel
    -0.63
     thence
    -0.63
    MockBean
    -0.61
    IGraphics
    -0.59
     CommonModule
    -0.59
    POSITIVE LOGITS
     how
    1.01
     hearing
    0.71
     seeing
    0.71
     propOrder
    0.69
     listening
    0.65
     watching
    0.62
     them
    0.61
     it
    0.59
     having
    0.58
     cómo
    0.55
    Activations Density 0.062%

    No Known Activations