© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11481
    Prev
    Next
    INDEX
    Explanations

    different varieties and qualities of tomatoes in cooking contexts

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

    tomatoes or tomato-related words

    np_acts-logits-general · gemini-2.0-flash

    tomato and sauce context

    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
    sizeCache
    -0.48
    ruptedException
    -0.46
    strument
    -0.44
    SupportActionBar
    -0.43
     outputStream
    -0.42
    RegistryLite
    -0.41
     Euphrates
    -0.41
    makeText
    -0.40
     henvisninger
    -0.40
    Chham
    -0.40
    POSITIVE LOGITS
     tomato
    0.93
    tomato
    0.91
     tomatoes
    0.90
    Tomato
    0.88
     Tomato
    0.87
     tomates
    0.84
     tomate
    0.83
     Tomatoes
    0.81
     Tomaten
    0.81
    🍅
    0.73
    Activations Density 0.325%

    No Known Activations