© 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. 18-GEMMASCOPE-RES-16K
    6. 1812
    Prev
    Next
    INDEX
    Explanations

    texts related to significant numerals and their implications

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

    Entering a business or building

    np_acts-logits-general · gemini-2.0-flash

    inside or entering public spaces

    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
    GEBURTS
    -0.51
    achting
    -0.47
     Belakang
    -0.44
     ویکی‌آمباردا
    -0.43
     północ
    -0.41
     elit
    -0.41
     AlertDialog
    -0.40
    ifon
    -0.40
     Hov
    -0.39
    ioren
    -0.39
    POSITIVE LOGITS
     negozio
    0.88
    Customers
    0.87
     店内
    0.85
     store
    0.85
    店内
    0.84
     inside
    0.83
     customers
    0.83
     interior
    0.83
    Inside
    0.82
     indoor
    0.81
    Activations Density 0.103%

    No Known Activations