© 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. 8447
    Prev
    Next
    INDEX
    Explanations

    mention of architectural terms and design-related concepts

    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
    writeFieldEnd
    -0.68
    tagHelperRunner
    -0.68
    zzleHttp
    -0.64
     للاسماء
    -0.63
     '\\;'
    -0.60
    TagMode
    -0.55
    WriteTagHelper
    -0.54
    jspb
    -0.50
    ThroughAttribute
    -0.49
     propOrder
    -0.47
    POSITIVE LOGITS
     architectural
    0.91
     architects
    0.88
     Architects
    0.88
     designers
    0.87
     design
    0.87
     designs
    0.86
     architect
    0.86
     Designers
    0.84
     Architectural
    0.82
     designer
    0.80
    Activations Density 0.097%

    No Known Activations