© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 11099
    Prev
    Next
    INDEX
    Explanations

    elements and properties in structured data formats, such as JSON

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.75
     Italijani
    -0.69
     disambiguazione
    -0.68
    StructEnd
    -0.67
    NewUrlParser
    -0.63
    IContainer
    -0.62
    homonymie
    -0.61
    drawal
    -0.61
    uxxxx
    -0.60
     <>",
    -0.60
    POSITIVE LOGITS
    localPosition
    0.53
     sub
    0.50
     finos
    0.49
    存于互联网档案馆
    0.47
    
    0.46
     innerhalb
    0.46
     propOrder
    0.46
    getSub
    0.45
    ciach
    0.45
     الرياضيه
    0.45
    Activations Density 0.977%

    No Known Activations