© 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. 36-GEMMASCOPE-RES-16K
    11. 8175
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries, especially those that are rhetorical or seek deeper understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.44
    EndGlobalSection
    -0.37
    BeginInit
    -0.36
    دانشنامهٔ
    -0.36
    iterranée
    -0.34
     belegt
    -0.32
    aneamente
    -0.30
    ActionMode
    -0.29
    最快更新
    -0.29
    
    -0.29
    POSITIVE LOGITS
     question
    3.50
     questions
    3.30
    question
    3.03
     Question
    2.94
    Question
    2.86
     Questions
    2.81
    questions
    2.80
     QUESTION
    2.77
    Questions
    2.73
     QUESTIONS
    2.59
    Activations Density 1.842%

    No Known Activations