Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13991
    Prev
    Next
    INDEX
    Explanations

    references to legal sentences or statutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UALA
    -0.56
     Calabria
    -0.56
     yaka
    -0.56
     Rimini
    -0.54
    anyahu
    -0.54
     للمعارف
    -0.53
    ayaquil
    -0.53
     phosphoric
    -0.53
    URBANA
    -0.53
    CHAFT
    -0.52
    POSITIVE LOGITS
     Albuquerque
    0.93
    buquerque
    0.83
    NM
    0.81
     NM
    0.80
    querque
    0.70
     Cruces
    0.69
    parsedMessage
    0.68
    :✨
    0.67
     Zia
    0.64
     New
    0.61
    Activations Density 0.207%

    No Known Activations