© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3853
    Prev
    Next
    INDEX
    Explanations

    references to organization, documentation, or reports in a professional or academic context

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

    Text after prepositions

    np_acts-logits-general · gemini-2.0-flash

    books and academic topics

    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
     للاسماء
    -0.53
     Gegenteil
    -0.35
     vuestros
    -0.33
     lambat
    -0.32
    getWriter
    -0.32
    IVEREF
    -0.32
     rotina
    -0.30
    İstinadlar
    -0.30
     aisladas
    -0.30
     kağıdı
    -0.30
    POSITIVE LOGITS
    gridy
    0.57
    IndentedString
    0.53
    Benson
    0.50
     '\\;'
    0.49
    canestro
    0.49
    uxxxx
    0.48
    ⤹
    0.48
    delwed
    0.47
    expandindo
    0.47
    Kab
    0.46
    Activations Density 0.296%

    No Known Activations