© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11092
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the combination of different qualities, characteristics, or functions in contexts such as work, collaboration, and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    
    -0.42
     Merah
    -0.38
    льга
    -0.37
    JspWriter
    -0.37
     CallOverrides
    -0.35
     piłkarz
    -0.35
     lemp
    -0.34
    斷
    -0.33
    hæng
    -0.33
     Wład
    -0.33
    POSITIVE LOGITS
     autorytatywna
    0.65
    yntaxException
    0.62
    RTEE
    0.49
    ImageContext
    0.44
    interopRequire
    0.44
    
    0.44
    IBOutlet
    0.44
    #+#
    0.43
     &___
    0.41
    кус
    0.40
    Activations Density 0.208%

    No Known Activations