© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10605
    Prev
    Next
    INDEX
    Explanations

    references to dry powders and powdered materials in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Powder" or "powdered" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    powder or powdered ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
    AsUp
    -0.72
    
    -0.60
    \{\\
    -0.59
    iſche
    -0.58
    ロウィン
    -0.58
     ſua
    -0.57
     ſuo
    -0.57
     fashiola
    -0.56
     Geſ
    -0.55
    ſſung
    -0.54
    POSITIVE LOGITS
     powder
    1.26
     Powder
    1.08
    Powder
    1.05
    powder
    0.97
     powders
    0.96
     powdered
    0.90
     poudre
    0.83
     powdery
    0.77
     bubuk
    0.77
     پودر
    0.72
    Activations Density 0.309%

    No Known Activations