© 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. 4504
    Prev
    Next
    INDEX
    Explanations

    terms related to dirt and dust

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

    "dust" or "dirt"

    np_acts-logits-general · gemini-2.0-flash

    dust and dirt

    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
    EndInit
    -0.78
    SuppressMessage
    -0.74
    StoryboardSegue
    -0.70
    stateProvider
    -0.69
    LookAnd
    -0.66
     betweenstory
    -0.65
     وتسجيلات
    -0.63
    AutoresizingMask
    -0.62
    Extinguishing
    -0.60
    ngdoc
    -0.57
    POSITIVE LOGITS
     dirt
    0.75
    bootstrapcdn
    0.74
    iness
    0.67
     dust
    0.67
    Dust
    0.66
    dirt
    0.66
     pollution
    0.64
    Dirt
    0.63
     dusted
    0.62
    AndEndTag
    0.61
    Activations Density 0.185%

    No Known Activations