© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 78149
    Prev
    Next
    INDEX
    Explanations

    references to wastewater management and treatment

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

    wastewater and related terms, wchar

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    fjspx
    -0.57
    picasso
    -0.57
    nativeElement
    -0.57
     propOrder
    -0.55
    UrlResolution
    -0.54
     Мексичка
    -0.53
    يكب
    -0.51
    tyfik
    -0.50
     فريبيس
    -0.50
    ьаж
    -0.50
    POSITIVE LOGITS
     wastewater
    2.00
     Wastewater
    1.84
     sewage
    0.93
     sewer
    0.84
     Sewage
    0.82
     sewerage
    0.82
     Sewer
    0.75
     Waterways
    0.63
     drainage
    0.60
     freshwater
    0.60
    Activations Density 0.003%

    No Known Activations