© 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-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12728
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases and questions related to choices or uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.38
     verse
    -0.35
     hObject
    -0.33
     mús
    -0.33
     repeated
    -0.33
     unknownFields
    -0.32
     continued
    -0.31
     vors
    -0.31
    Veja
    -0.30
     ведь
    -0.30
    POSITIVE LOGITS
    存于互联网档案馆
    0.66
    verwijspagina
    0.62
    encodeWith
    0.61
    GEBURTS
    0.59
     EconPapers
    0.55
     ***!
    0.55
    Personendaten
    0.55
    homonymie
    0.55
    الدراسه
    0.54
     ligiloj
    0.54
    Activations Density 0.129%

    No Known Activations