© 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. 14530
    Prev
    Next
    INDEX
    Explanations

    references to property damage and its implications

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

    Parts of buildings/houses

    np_acts-logits-general · gemini-2.0-flash

    house components and issues

    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
    igné
    -0.46
     Reverso
    -0.45
     spé
    -0.44
     kife
    -0.42
     navire
    -0.38
     ἀ
    -0.38
    뉘
    -0.37
    voyage
    -0.37
     doux
    -0.37
    Componentes
    -0.37
    POSITIVE LOGITS
     plumbing
    1.27
     gutters
    1.10
     heating
    1.08
     HVAC
    1.07
     windows
    1.06
     roofs
    1.03
     electrical
    1.03
     septic
    1.00
     flooring
    0.99
     sewer
    0.99
    Activations Density 0.284%

    No Known Activations