© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 12011
    Prev
    Next
    INDEX
    Explanations

    questions and phrases indicating curiosity or inquiry

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Question words

    np_acts-logits-general · gemini-2.0-flash

    who followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ANTY
    -0.35
    SharedDtor
    -0.35
    Nep
    -0.34
    neither
    -0.34
    Rag
    -0.34
     саме
    -0.34
    FunctionFlags
    -0.33
     Raised
    -0.33
     processes
    -0.33
     becauſe
    -0.32
    POSITIVE LOGITS
    httphttps
    0.74
     ProtoMessage
    0.54
     يتيمه
    0.52
     considérons
    0.52
    Tikang
    0.49
    unknownFields
    0.48
    webElementXpaths
    0.48
    chowa
    0.48
    ?).
    0.48
    moveToFirst
    0.47
    Activations Density 0.158%

    No Known Activations