© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8597
    Prev
    Next
    INDEX
    Explanations

    phrases related to progressions or sequences in processes, particularly in a formal or instructional context

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

    "course" and its variations

    np_acts-logits-general · gemini-2.0-flash

    course of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    🏻
    -0.76
    setContentView
    -0.74
    脚注の使い方
    -0.71
    🏼
    -0.70
    🏾
    -0.69
    ">',
    -0.68
    🏽
    -0.67
     HasFactory
    -0.64
    AsUp
    -0.64
    ſelf
    -0.64
    POSITIVE LOGITS
     courses
    1.10
     Courses
    1.07
    Courses
    0.98
    courses
    0.91
     COURSES
    0.86
    course
    0.85
     COURSE
    0.84
     course
    0.83
     Course
    0.83
     Cours
    0.83
    Activations Density 0.133%

    No Known Activations