© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9555
    Prev
    Next
    INDEX
    Explanations

    various mentions and contexts related to tea, including its consumption, types, and associated cultural practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.52
    __*/
    -0.48
     estekak
    -0.47
    IBarButtonItem
    -0.43
    arriver
    -0.42
     Италијани
    -0.40
     strconv
    -0.40
     benefits
    -0.40
    retz
    -0.39
    Földrajz
    -0.39
    POSITIVE LOGITS
     tea
    1.96
     Tea
    1.84
    Tea
    1.80
     TEA
    1.52
    tea
    1.40
    茶
    1.38
    TEA
    1.36
     čaj
    1.34
     teas
    1.26
     Teas
    1.22
    Activations Density 0.151%

    No Known Activations