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-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 10536
    Prev
    Next
    INDEX
    Explanations

    references to creativity in relation to consumerism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.48
    Étymologie
    -0.42
    帖最后由
    -0.41
    DIPSETTING
    -0.41
    FunctionFlags
    -0.40
     kiin
    -0.39
    baguna
    -0.39
     TreeMap
    -0.39
     locaux
    -0.38
     Gesetzes
    -0.38
    POSITIVE LOGITS
     consumer
    0.91
     culture
    0.81
     consumption
    0.78
    consumer
    0.73
     mass
    0.72
     consumo
    0.69
     advertising
    0.68
     consume
    0.68
     Consumer
    0.68
     media
    0.66
    Activations Density 0.658%

    No Known Activations