© 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-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15356
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and procedural concepts, particularly related to court circuits and case law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pinocchio
    -0.55
     ujednoznacz
    -0.54
     EconPapers
    -0.49
     henkil
    -0.48
    enares
    -0.48
    賂
    -0.47
     kanssa
    -0.47
    abank
    -0.46
    illoma
    -0.46
    etCode
    -0.45
    POSITIVE LOGITS
    7
    1.14
     Seven
    1.08
     seven
    1.04
     Seventh
    1.03
     seventh
    1.00
    Seventh
    0.98
     SEVEN
    0.93
    Seven
    0.93
     sieben
    0.88
     SEVENTH
    0.88
    Activations Density 0.569%

    No Known Activations