© 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. 11706
    Prev
    Next
    INDEX
    Explanations

    mentions of grants and institutional funding sources

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

    Numbers or symbols after periods, commas, or asterisks

    np_acts-logits-general · gemini-2.0-flash

    russian names and places

    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
     муніципалі
    -0.62
    nocení
    -0.56
    НОСТИ
    -0.54
    thâu
    -0.52
    НОЙ
    -0.49
    СТВА
    -0.49
    piratory
    -0.48
    faatkan
    -0.48
     године
    -0.48
    Kjelder
    -0.47
    POSITIVE LOGITS
     Russian
    0.95
     Moscow
    0.83
    Russian
    0.81
     Sergey
    0.80
     Dmitry
    0.78
     Russia
    0.78
     Alexey
    0.77
     russian
    0.75
     Sergei
    0.75
     Soviet
    0.74
    Activations Density 0.482%

    No Known Activations