© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6345
    Prev
    Next
    INDEX
    Explanations

    financial transactions and real estate-related activities

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

    Real estate and housing

    np_acts-logits-general · gemini-2.0-flash

    housing and apartments

    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
     '\\;'
    -0.73
    mybatisplus
    -0.67
     Wiktionnaire
    -0.64
     defaultstate
    -0.63
    Географиясе
    -0.62
    TableHead
    -0.60
    GEBURTSDATUM
    -0.58
     iprot
    -0.56
    pfung
    -0.54
     <=",
    -0.54
    POSITIVE LOGITS
     flats
    0.92
     apartments
    0.90
     apartment
    0.88
    Apartment
    0.83
     Apartment
    0.82
     appartements
    0.79
    flats
    0.77
     Flats
    0.76
     Apartments
    0.74
     plot
    0.73
    Activations Density 0.100%

    No Known Activations