Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3914
    Prev
    Next
    INDEX
    Explanations

    terms related to plumbing fixtures and their functionality

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

    associated with toilets and flushing

    np_acts-logits-general · gemini-2.0-flash

    toilet flush

    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
    imageshack
    -0.58
    CppMethod
    -0.57
     Paglinawan
    -0.57
     الحره
    -0.54
     مرئيه
    -0.53
     تضيفلها
    -0.52
    SharedCtor
    -0.50
    ьаж
    -0.50
    ImageContext
    -0.49
    gnore
    -0.49
    POSITIVE LOGITS
     toilet
    0.50
     flush
    0.49
     Toilet
    0.41
     flushing
    0.41
     Flush
    0.40
    Toilet
    0.39
    flush
    0.38
     toilets
    0.37
     flushed
    0.37
    Flush
    0.35
    Activations Density 0.186%

    No Known Activations