© 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. 11-GEMMASCOPE-RES-16K
    11. 5064
    Prev
    Next
    INDEX
    Explanations

    references to schedules, assignments, and arrangements related to contracts and the academic calendar

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    AndEndTag
    -0.69
     ब्रेकडाउन
    -0.66
     otomatig
    -0.65
    RenderAtEndOf
    -0.63
    hilangan
    -0.62
    XmlEnum
    -0.57
     resourceCulture
    -0.56
    Vidite
    -0.53
    mobileqq
    -0.53
     متعلقه
    -0.52
    POSITIVE LOGITS
    SharedCtor
    0.37
     offseason
    0.34
     gab
    0.34
     NUKAT
    0.33
     season
    0.31
     Lif
    0.30
     winter
    0.30
     Convention
    0.29
     preseason
    0.29
     Gad
    0.29
    Activations Density 0.344%

    No Known Activations