Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 6128
    Prev
    Next
    INDEX
    Explanations

    references to alcoholic beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vitamina
    -0.56
    Responder
    -0.54
     Millard
    -0.54
     loss
    -0.53
    atasaray
    -0.51
     bolsa
    -0.49
     zuge
    -0.48
    كذا
    -0.48
     solare
    -0.48
     nido
    -0.47
    POSITIVE LOGITS
     Beer
    1.62
     beer
    1.60
    Beer
    1.53
     BEER
    1.49
    beer
    1.44
     beers
    1.35
     wine
    1.32
     brewery
    1.30
     Beers
    1.28
     tequila
    1.27
    Activations Density 2.417%

    No Known Activations