© 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. 18-GEMMASCOPE-RES-16K
    11. 10935
    Prev
    Next
    INDEX
    Explanations

    details related to property features and conditions

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

    Parts of a house

    np_acts-logits-general · gemini-2.0-flash

    garage and basement locations

    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
    Portale
    -0.72
     getResource
    -0.62
    hdys
    -0.62
     stethoscope
    -0.56
    Geplaatst
    -0.55
     táctil
    -0.54
    spesies
    -0.53
    +#+#
    -0.52
     nakalista
    -0.50
     hospitales
    -0.50
    POSITIVE LOGITS
     garage
    0.93
     Garage
    0.76
     basement
    0.75
    Garage
    0.72
     garages
    0.71
    garage
    0.70
     backyard
    0.69
     septic
    0.68
     carport
    0.67
     laundry
    0.59
    Activations Density 0.046%

    No Known Activations