© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 124262
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a large variety or abundance of something

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

    a multitude of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.50
    IntoConstraints
    -0.38
    原始内容存档于
    -0.37
    openSession
    -0.36
     agak
    -0.36
     spä
    -0.35
    Хьажоргаш
    -0.34
    postIndex
    -0.34
     Judging
    -0.34
    maler
    -0.34
    POSITIVE LOGITS
     myriad
    0.85
     plethora
    0.81
    riad
    0.75
     множество
    0.75
     numerous
    0.75
     countless
    0.75
     beragam
    0.73
     pelbagai
    0.68
     multitude
    0.67
     MANY
    0.67
    Activations Density 0.017%

    No Known Activations