© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 10874
    Prev
    Next
    INDEX
    Explanations

    questions about specific word usage and phrasing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
     …
    -0.49
     L
    -0.44
     ground
    -0.43
     due
    -0.43
     l
    -0.42
     e
    -0.42
     […]
    -0.42
     
    -0.41
     ka
    -0.40
     Mag
    -0.39
    POSITIVE LOGITS
     kaarangay
    1.16
    MessageOf
    1.09
     betweenstory
    1.00
     ویکی‌پدی
    0.98
    featureID
    0.97
     propOrder
    0.93
    astéroïdes
    0.92
    richTextPanel
    0.92
    ьаж
    0.91
     pinulongan
    0.90
    Activations Density 0.592%

    No Known Activations