© 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. 24-GEMMASCOPE-RES-16K
    11. 1108
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases that emphasize intensity or abundance

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

    "so" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    so followed by descriptive word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     certificación
    -0.48
     elástica
    -0.44
     electrónica
    -0.43
    kozás
    -0.42
    릎
    -0.41
     especializada
    -0.40
    werb
    -0.40
    lceil
    -0.39
    ท์
    -0.39
     finanzas
    -0.39
    POSITIVE LOGITS
     nahilalakip
    1.01
     المعيارى
    0.94
    TypedDataSet
    0.87
     AssemblyCulture
    0.79
     SO
    0.77
    AddTagHelper
    0.76
    So
    0.75
     So
    0.73
    出版年
    0.72
     EconPapers
    0.71
    Activations Density 0.118%

    No Known Activations