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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1569
    Prev
    Next
    INDEX
    Explanations

    terms related to consumption and dietary habits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     Asser
    -0.59
    endregion
    -0.58
    퀀
    -0.52
    ProjectId
    -0.51
     projectId
    -0.50
     perfect
    -0.48
    actylus
    -0.48
    orghini
    -0.48
    ppert
    -0.48
     autorytatywna
    -0.47
    POSITIVE LOGITS
     consumption
    0.68
     consommation
    0.67
    Consumption
    0.66
     Consumo
    0.64
    consumption
    0.64
     consumo
    0.64
     Consume
    0.64
     consumed
    0.63
    Eating
    0.62
     Consumption
    0.62
    Activations Density 0.390%

    No Known Activations