© 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. 12643
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate intent or purpose

    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
    wakili
    -0.56
     verantwoorde
    -0.49
     épa
    -0.48
     handleMessage
    -0.47
    bags
    -0.46
     useAuth
    -0.46
    endphp
    -0.45
     liggen
    -0.45
     Responsibility
    -0.43
     beschik
    -0.43
    POSITIVE LOGITS
     כדי
    0.79
     inorder
    0.77
     щоб
    0.76
     чтобы
    0.73
     Чтобы
    0.73
    Чтобы
    0.67
    为了
    0.66
    inorder
    0.65
    為了
    0.64
    Derbyniad
    0.64
    Activations Density 0.177%

    No Known Activations