© 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. 27780
    Prev
    Next
    INDEX
    Explanations

    the adverb "just" and its strong occurrences in various contexts

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

    just + verb

    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
     wpływ
    -0.30
    lcccc
    -0.30
     różne
    -0.27
     szczegó
    -0.27
     nantinya
    -0.27
     étroite
    -0.26
     zimowe
    -0.26
     estrecha
    -0.25
    intă
    -0.24
     naturligt
    -0.24
    POSITIVE LOGITS
     zwiſchen
    0.73
     Administrativna
    0.72
    ﹧
    0.71
     للتو
    0.70
    UnusedPrivate
    0.69
    recently
    0.69
     erſten
    0.68
    <unused80>
    0.67
    <unused52>
    0.67
    <unused47>
    0.67
    Activations Density 0.009%

    No Known Activations