© 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. 37823
    Prev
    Next
    INDEX
    Explanations

    technical or specialized terms and classifications

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

    types, schemes, bearings, styles

    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
     utafitiHapana
    -0.85
     للاسماء
    -0.76
    antMatchers
    -0.69
    writeFieldEnd
    -0.68
     المعيارى
    -0.67
    RTLI
    -0.62
    MLLoader
    -0.61
    iſen
    -0.60
     censiti
    -0.60
    httphttps
    -0.59
    POSITIVE LOGITS
     Verhältnisse
    0.46
     cuerda
    0.36
     flexível
    0.34
     partial
    0.33
     modalidad
    0.33
     situazioni
    0.32
     tercih
    0.32
     stos
    0.32
     soluzioni
    0.32
     giras
    0.31
    Activations Density 0.089%

    No Known Activations