© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 974
    Prev
    Next
    INDEX
    Explanations

    references to property and housing conditions

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

    Home repair, construction, or related issues

    np_acts-logits-general · gemini-2.0-flash

    home features and defects

    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
     industriels
    -0.54
     burbujas
    -0.51
     amostra
    -0.49
     médaille
    -0.49
     kife
    -0.48
     vectorielles
    -0.47
     algoritmo
    -0.46
     mères
    -0.46
     penurunan
    -0.45
     concernés
    -0.45
    POSITIVE LOGITS
     plumbing
    1.38
     roof
    1.20
     lighting
    1.19
     flooring
    1.18
     windows
    1.18
     HVAC
    1.17
     heating
    1.16
     wiring
    1.13
     floors
    1.13
     furniture
    1.11
    Activations Density 0.229%

    No Known Activations