© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2332
    Prev
    Next
    INDEX
    Explanations

    structured information and specific details in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    كويكب
    -0.57
     NSCoder
    -0.56
    ArrowToggle
    -0.56
    HasAnnotation
    -0.55
    
    -0.52
    +#+
    -0.49
    DoubleQuotes
    -0.49
    солю
    -0.47
    parsedMessage
    -0.47
    StructEnd
    -0.47
    POSITIVE LOGITS
     page
    2.97
     pages
    2.61
    page
    2.55
     Page
    2.34
    Page
    2.27
    pages
    2.15
     PAGE
    2.12
     Pages
    2.05
     pagina
    1.96
    PAGE
    1.93
    Activations Density 0.383%

    No Known Activations