© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11715
    Prev
    Next
    INDEX
    Explanations

    terms indicating exclusivity or limited availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.57
    bootstrapcdn
    -0.57
     ainfi
    -0.54
    Autoritní
    -0.54
     viewDidLoad
    -0.54
     turista
    -0.54
     ſtate
    -0.53
    pecabe
    -0.50
     enfans
    -0.49
    хьтан
    -0.49
    POSITIVE LOGITS
     exclusive
    2.03
    Exclusive
    1.86
    exclusive
    1.84
     Exclusive
    1.80
     EXCLUSIVE
    1.65
     exclusively
    1.61
     Exclu
    1.61
    EXCLUSIVE
    1.53
    exclu
    1.52
     exclusivity
    1.52
    Activations Density 0.248%

    No Known Activations