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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2380
    Prev
    Next
    INDEX
    Explanations

    references to the Supreme Court and its rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.71
    товано
    -0.63
    sstream
    -0.59
    ổi
    -0.58
     Freitas
    -0.58
    beutel
    -0.57
    kaŭ
    -0.57
    virons
    -0.57
    กก
    -0.55
     Supp
    -0.55
    POSITIVE LOGITS
     Supreme
    2.01
    Supreme
    1.70
     SUPREME
    1.50
     supreme
    1.33
    supreme
    1.19
     suprême
    1.13
     Supremo
    1.06
     SCOT
    0.97
     Верхов
    0.96
     justices
    0.90
    Activations Density 0.115%

    No Known Activations