© 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. 28-GEMMASCOPE-RES-16K
    11. 5232
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation used for dialogue

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

    after quotation marks

    np_acts-logits-general · gemini-2.0-flash

    steel capillary

    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
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.55
     autorytatywna
    -0.47
     pieza
    -0.43
    RenderAtEndOf
    -0.42
     everywhere
    -0.40
     nø
    -0.40
     resourceCulture
    -0.38
     piece
    -0.38
     ilman
    -0.38
    点此举报
    -0.38
    POSITIVE LOGITS
     said
    1.09
     says
    0.87
    said
    0.76
     wrote
    0.71
    says
    0.69
     commented
    0.61
     Says
    0.60
     sagte
    0.57
     exclaimed
    0.56
     remarked
    0.54
    Activations Density 0.056%

    No Known Activations