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. 21-GEMMASCOPE-RES-16K
    6. 15100
    Prev
    Next
    INDEX
    Explanations

    discussions about coffee quality and related experiences

    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
    riwal
    -0.64
     termites
    -0.63
    ValueStyle
    -0.63
     Fische
    -0.62
     alimentaires
    -0.61
    ंदीखरीदारी
    -0.61
     tetanus
    -0.58
     termite
    -0.57
    WebControls
    -0.56
     Ples
    -0.56
    POSITIVE LOGITS
     coffee
    2.16
     Coffee
    1.86
    Coffee
    1.78
    coffee
    1.76
     coffees
    1.70
     COFFEE
    1.66
     espresso
    1.60
     barista
    1.53
     Coffe
    1.53
     coffe
    1.52
    Activations Density 0.095%

    No Known Activations