© 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. 14650
    Prev
    Next
    INDEX
    Explanations

    references to RNA interference and the specific RNA elements involved in gene silencing mechanisms

    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
     '\\;'
    -0.97
    Cyfeiriadau
    -0.78
    ReusableCell
    -0.72
    dersfield
    -0.70
     DPM
    -0.70
    AsUp
    -0.69
     numerus
    -0.68
    
    -0.67
    ViewImports
    -0.66
     unknownFields
    -0.66
    POSITIVE LOGITS
    addCriterion
    0.54
     оригіналу
    0.52
     target
    0.48
    śla
    0.47
    serviceWorker
    0.44
     št
    0.43
     Woh
    0.43
    CRYPT
    0.41
    MessageDigest
    0.41
    SuppressMessage
    0.41
    Activations Density 0.970%

    No Known Activations