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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14312
    Prev
    Next
    INDEX
    Explanations

    terms associated with wasting time and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.87
     InputDecoration
    -0.74
    jooq
    -0.73
    InjectAttribute
    -0.73
    хьтан
    -0.72
    FieldBuilder
    -0.71
     ComVisible
    -0.70
    ModelAdmin
    -0.69
     fieldNum
    -0.67
    رشف
    -0.66
    POSITIVE LOGITS
     resources
    2.00
     Resources
    1.63
    resources
    1.56
     RESOURCES
    1.50
    Resources
    1.48
     ressources
    1.46
     resource
    1.38
     Ressourcen
    1.33
    资源
    1.27
    RESOURCES
    1.26
    Activations Density 0.236%

    No Known Activations