© 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. 24-GEMMASCOPE-RES-16K
    11. 4841
    Prev
    Next
    INDEX
    Explanations

    terms related to home maintenance and cleaning practices

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

    floors and flooring

    np_acts-logits-general · gemini-2.0-flash

    flooring materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.66
    rrggbb
    -0.62
    esez
    -0.55
    nelson
    -0.52
     wasps
    -0.52
     Dink
    -0.52
    Roster
    -0.51
    RenderAtEndOf
    -0.51
    Jesmyn
    -0.50
     wasp
    -0.50
    POSITIVE LOGITS
     floor
    1.51
     flooring
    1.48
     floors
    1.41
     Floor
    1.37
    floor
    1.30
    Floor
    1.29
     FLOOR
    1.27
     Floors
    1.26
     carpet
    1.22
     Flooring
    1.21
    Activations Density 0.097%

    No Known Activations