© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 10209
    Prev
    Next
    INDEX
    Explanations

    legal terms and expressions associated with medical malpractice and injury claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    참고
    -0.54
     ✭✭
    -0.54
    scape
    -0.53
    jame
    -0.52
     licked
    -0.52
    々
    -0.51
     apologised
    -0.51
    PRNewswire
    -0.49
    Ход
    -0.49
    kosh
    -0.49
    POSITIVE LOGITS
     clause
    0.67
     provisions
    0.66
     provision
    0.58
     (§
    0.54
     charges
    0.54
     agreement
    0.53
     requirements
    0.52
    provision
    0.52
     EconPapers
    0.52
    ExceptionHandler
    0.52
    Activations Density 1.212%

    No Known Activations