© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4548
    Prev
    Next
    INDEX
    Explanations

    medical terms and concepts related to surgical procedures

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

    Plumbing and pipe related texts

    np_acts-logits-general · gemini-2.0-flash

    plumbing systems and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gyrus
    -0.68
     pinulongan
    -0.58
     Audiodateien
    -0.58
    Попис
    -0.58
     تضيفلها
    -0.57
    romyalgia
    -0.56
     incub
    -0.56
    Breadcrumb
    -0.56
    TargetException
    -0.55
    Autoritní
    -0.54
    POSITIVE LOGITS
     plumbing
    0.94
     pipe
    0.91
     pump
    0.91
     pipes
    0.91
     flow
    0.86
     pumps
    0.86
     Plumbing
    0.84
     hose
    0.83
    pump
    0.82
    pipe
    0.81
    Activations Density 0.454%

    No Known Activations