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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9048
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditionality and relationships between subjects and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows personal pronouns and negations

    np_acts-logits-general · gemini-2.0-flash

    certainly not, never

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     nothing
    -0.77
     no
    -0.77
     aucune
    -0.73
    无
    -0.71
    Nothing
    -0.70
     nessuna
    -0.70
    no
    -0.69
     कोई
    -0.68
     Aucun
    -0.68
     rien
    -0.68
    POSITIVE LOGITS
    ScopeManager
    0.91
    URLException
    0.80
    portál
    0.79
    ParallelGroup
    0.76
    存于互联网档案馆
    0.72
     المعيارى
    0.72
    
    0.71
    webElementXpaths
    0.70
    afficheront
    0.68
    ucket
    0.68
    Activations Density 0.266%

    No Known Activations