© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 20372
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to comparisons and relationships in data

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

    prepositions followed by descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite

    statements expressing measurement, dependence, or causal/functional relationships in technical or scientific text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     Administrativna
    -0.90
     Мексичка
    -0.82
     otomatig
    -0.66
    GOTREF
    -0.62
     tartalomajánló
    -0.60
     Италијани
    -0.60
     Italijani
    -0.59
     propOrder
    -0.59
     Taktlose
    -0.58
    :✨
    -0.54
    POSITIVE LOGITS
    forChild
    0.55
     Green
    0.46
    pannt
    0.46
    zoo
    0.45
    ivo
    0.44
    ssy
    0.44
     
    0.43
    CEA
    0.42
     Greens
    0.42
    ire
    0.42
    Activations Density 1.011%

    No Known Activations