© 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. 14-GEMMASCOPE-RES-16K
    11. 8394
    Prev
    Next
    INDEX
    Explanations

    entities related to educational and research organizations, particularly in the fields of arts, health, technology, and sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gjø
    -0.49
    fjspx
    -0.47
     rhestr
    -0.47
     devolución
    -0.46
     ayudarte
    -0.46
     nemlig
    -0.46
     specchio
    -0.46
     eenvou
    -0.46
     húmedo
    -0.46
     sufrido
    -0.46
    POSITIVE LOGITS
    ConstraintMaker
    0.50
    :✨
    0.47
    \{\\
    0.46
     Prison
    0.42
     departament
    0.41
    RTDA
    0.41
     prison
    0.39
    
    0.39
    marathon
    0.39
     ""],
    0.38
    Activations Density 0.325%

    No Known Activations