© 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. 9-GEMMASCOPE-RES-16K
    11. 10053
    Prev
    Next
    INDEX
    Explanations

    specific terms and structured information related to brands, products, or corporate entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.64
     perchè
    -0.61
     loosing
    -0.60
    ="@+
    -0.59
    +#+#
    -0.58
     dimana
    -0.56
    ]=>
    -0.56
     betek
    -0.56
    UnusedPrivate
    -0.56
    TagMode
    -0.55
    POSITIVE LOGITS
     –,
    0.64
     nonnegative
    0.62
    更好地
    0.61
     به‌عنوان
    0.60
    ,’”
    0.56
     État
    0.54
     Asimismo
    0.52
     derselben
    0.52
     Afterward
    0.51
     afterward
    0.51
    Activations Density 2.799%

    No Known Activations