© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3825
    Prev
    Next
    INDEX
    Explanations

    terms related to cleaning and maintenance of carpets and flooring

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

    flooring or carpets

    np_acts-logits-general · gemini-2.0-flash

    carpet and flooring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.73
    WarningLevel
    -0.64
    esez
    -0.62
    ⓧ
    -0.59
     insuffisamment
    -0.55
    nelson
    -0.52
     wasp
    -0.52
     wasps
    -0.52
     confira
    -0.51
    VIAF
    -0.51
    POSITIVE LOGITS
     floor
    1.67
     flooring
    1.64
     Floor
    1.54
     floors
    1.50
    Floor
    1.47
     carpet
    1.46
     FLOOR
    1.45
    floor
    1.44
     Flooring
    1.41
     Floors
    1.35
    Activations Density 0.083%

    No Known Activations