© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6526
    Prev
    Next
    INDEX
    Explanations

    frequent usage of the adverb "often."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Спољашње
    -0.87
     stringBuilder
    -0.80
     Reim
    -0.79
    脚注の使い方
    -0.79
    kész
    -0.73
    hydrogenase
    -0.73
     initializer
    -0.73
    Pande
    -0.71
    ModelAdmin
    -0.71
    DataBinding
    -0.70
    POSITIVE LOGITS
     often
    1.44
     Often
    1.33
    often
    1.29
    Often
    1.27
     menudo
    1.08
     Orrell
    1.00
     times
    0.95
     frequently
    0.94
     souvent
    0.92
     Frequently
    0.90
    Activations Density 0.060%

    No Known Activations