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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2842
    Prev
    Next
    INDEX
    Explanations

    mentions of coffee and related beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AntiForgeryToken
    -0.71
    AlterField
    -0.71
    ]")]
    -0.68
     bata
    -0.67
    rungsseite
    -0.64
     sportback
    -0.64
     Clarion
    -0.64
     cipolla
    -0.64
    pdb
    -0.63
     Garth
    -0.63
    POSITIVE LOGITS
     coffee
    1.72
    coffee
    1.57
     Coffee
    1.56
    Coffee
    1.54
     coffe
    1.50
     COFFEE
    1.39
     coffees
    1.38
     tea
    1.34
     Coffe
    1.30
     espresso
    1.19
    Activations Density 0.194%

    No Known Activations