© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13170
    Prev
    Next
    INDEX
    Explanations

    phrases related to reading and reviews

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

    "Read full review/article" phrases

    np_acts-logits-general · gemini-2.0-flash

    full article or review

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    IVEREF
    -0.57
    GEBURTSDATUM
    -0.56
    AnimationsModule
    -0.56
    JspWriter
    -0.56
     kasarigan
    -0.54
     AssemblyVersion
    -0.53
    ValueStyle
    -0.53
    stylers
    -0.51
    RetentionPolicy
    -0.50
    شهاد
    -0.50
    POSITIVE LOGITS
    devamını
    0.48
    Weiterlesen
    0.45
    layoutControl
    0.41
    LoadMore
    0.34
    Читать
    0.33
     Kontext
    0.33
    openqa
    0.32
    loadMore
    0.32
    続きを読む
    0.32
     story
    0.31
    Activations Density 0.250%

    No Known Activations