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. 0-GEMMASCOPE-RES-16K
    6. 6649
    Prev
    Next
    INDEX
    Explanations

    expressions of overwhelming emotions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.96
     fometimes
    -0.95
     Jefus
    -0.93
     AssemblyVersion
    -0.93
     Chriftian
    -0.91
     Shakspeare
    -0.91
     fubject
    -0.90
    JspWriter
    -0.89
    tanleria
    -0.88
     doubtnut
    -0.87
    POSITIVE LOGITS
     overwhelming
    0.85
     monitoring
    0.72
     Monitoring
    0.63
     monitors
    0.62
    §
    0.59
    vast
    0.58
     vast
    0.57
     Marshall
    0.56
     monitor
    0.56
    whelming
    0.55
    Activations Density 0.209%

    No Known Activations