© 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. 24-GEMMASCOPE-RES-16K
    11. 5047
    Prev
    Next
    INDEX
    Explanations

    arguments and justifications for various positions and actions

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

    Tokens following discourse markers/transitional words

    np_acts-logits-general · gemini-2.0-flash

    transition words and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.65
    IContainer
    -0.58
    ServletException
    -0.58
    majánló
    -0.52
     JAXBElement
    -0.52
     videoc
    -0.49
    Cô
    -0.48
     UserInfo
    -0.48
     }{@
    -0.48
     plat
    -0.47
    POSITIVE LOGITS
    Personensuche
    0.51
     Vorteile
    0.43
     it
    0.38
     HttpNotFound
    0.36
     ventaja
    0.36
     pozwala
    0.35
     usarlo
    0.35
     vantaggio
    0.35
     improves
    0.35
    AddHtmlAttribute
    0.34
    Activations Density 0.388%

    No Known Activations