© 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. 23-GEMMASCOPE-RES-16K
    11. 10848
    Prev
    Next
    INDEX
    Explanations

    elements related to spatial organization and furniture arrangement in living spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нент
    -0.59
     retardation
    -0.50
    warnai
    -0.47
     सत्यापित
    -0.46
    esters
    -0.44
     Curie
    -0.44
    undred
    -0.43
     database
    -0.43
    Await
    -0.43
    Carreira
    -0.43
    POSITIVE LOGITS
     cramped
    1.14
     spacious
    1.01
     space
    0.94
     roomy
    0.93
     claust
    0.91
     accommodates
    0.89
     maximized
    0.87
     accommodate
    0.87
     accommodating
    0.86
     multipurpose
    0.85
    Activations Density 0.192%

    No Known Activations