© 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. 6-GEMMASCOPE-RES-16K
    11. 13215
    Prev
    Next
    INDEX
    Explanations

    phrases that signal actions taking place in past and present contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cæsar
    -0.74
     Efq
    -0.66
     Easton
    -0.66
     airway
    -0.62
     schooner
    -0.62
     Maud
    -0.62
    oban
    -0.61
     unwritten
    -0.61
     Bede
    -0.61
     Otta
    -0.61
    POSITIVE LOGITS
     While
    1.13
     while
    1.11
    While
    1.09
    Während
    1.03
    while
    0.98
     während
    0.97
     enquanto
    0.96
    WHILE
    0.96
     WHILE
    0.95
    mientras
    0.94
    Activations Density 0.145%

    No Known Activations