© 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
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13297
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and operations involving tensor products and vector spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reportWebVitals
    -0.34
    milch
    -0.32
    romyalgia
    -0.30
     inconnu
    -0.30
    uklu
    -0.30
    ütü
    -0.28
     kesk
    -0.28
    üğ
    -0.27
    cování
    -0.27
     fuch
    -0.27
    POSITIVE LOGITS
    webElementXpaths
    0.67
    otimes
    0.66
     للاسماء
    0.63
     Roskov
    0.59
    migrationBuilder
    0.59
     tartalomajánló
    0.55
    Datuak
    0.54
     kasarigan
    0.54
     الحره
    0.54
    NameInMap
    0.54
    Activations Density 1.039%

    No Known Activations