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. 21-GEMMASCOPE-RES-16K
    6. 641
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court proceedings and sentencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ayaquil
    -0.64
    CHAFT
    -0.59
     Straits
    -0.57
    APORE
    -0.56
     yaka
    -0.55
     mola
    -0.54
     Haitian
    -0.54
    UALA
    -0.54
     phosphoric
    -0.53
    URBANA
    -0.53
    POSITIVE LOGITS
     Albuquerque
    0.90
    buquerque
    0.82
    NM
    0.77
     NM
    0.75
    querque
    0.72
     Zia
    0.65
     Cruces
    0.62
     Lob
    0.59
    :✨
    0.59
     Baca
    0.57
    Activations Density 0.134%

    No Known Activations