© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8149
    Prev
    Next
    INDEX
    Explanations

    references to judicial opinions and dissenting justices

    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
     diken
    -0.50
    msgid
    -0.50
    HtmlAttribute
    -0.50
    TRAILING
    -0.50
    toBeTruthy
    -0.49
     везе
    -0.48
    Hozzáférés
    -0.48
    guerite
    -0.47
     Agamemnon
    -0.47
    sete
    -0.46
    POSITIVE LOGITS
     Justices
    1.19
     justices
    1.16
     Supreme
    0.99
     SCOT
    0.98
    Supreme
    0.97
     SUPREME
    0.85
     judges
    0.85
     Judges
    0.80
    Jus
    0.79
     dissenting
    0.78
    Activations Density 1.583%

    No Known Activations