© 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. 7-GEMMASCOPE-RES-16K
    6. 15100
    Prev
    Next
    INDEX
    Explanations

    references to dust and its various contexts and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.47
    WriteTagHelper
    -0.43
    therapeutic
    -0.37
     neop
    -0.36
     JUGA
    -0.35
     therapeutic
    -0.35
     therapeu
    -0.35
    gwt
    -0.34
     vectra
    -0.34
    exp
    -0.33
    POSITIVE LOGITS
     dust
    2.38
     Dust
    2.16
    Dust
    2.11
     powder
    2.02
    dust
    2.00
     DUST
    1.98
     Powder
    1.93
    Powder
    1.87
     polvo
    1.84
    powder
    1.81
    Activations Density 0.212%

    No Known Activations