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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 17788
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries, particularly those beginning with "What," "How," or "Why."

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

    asking "what is" or "why"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     autorytatywna
    -0.91
     Normdatei
    -0.91
    Personensuche
    -0.89
    
    -0.88
    oredCriteria
    -0.83
     AssemblyCompany
    -0.82
     AttributeSet
    -0.80
    transQ
    -0.77
    原始内容存档于
    -0.76
    InitVars
    -0.76
    POSITIVE LOGITS
    落
    0.41
    Impl
    0.34
     落
    0.33
    LineEdit
    0.32
    es
    0.32
     Caribe
    0.31
    impl
    0.31
     
    0.31
     fully
    0.31
     true
    0.31
    Activations Density 0.052%

    No Known Activations