© 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. 2-GEMMASCOPE-RES-16K
    11. 15850
    Prev
    Next
    INDEX
    Explanations

    expressions of affection or admiration, particularly using the word "lovely."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.69
     Witherspoon
    -0.69
     titoli
    -0.64
     Dink
    -0.60
     Biggs
    -0.58
     Vito
    -0.58
     Freeport
    -0.58
     sekali
    -0.56
    yki
    -0.56
    enumi
    -0.55
    POSITIVE LOGITS
     lovely
    1.12
    lovely
    0.99
     Lovely
    0.92
    Lovely
    0.90
    RegistryLite
    0.70
     pleasant
    0.69
     nice
    0.69
     QtCore
    0.67
     nicest
    0.67
     unpleasant
    0.65
    Activations Density 0.050%

    No Known Activations