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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 11873
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to duty of care and negligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     softly
    -0.57
    IMPORTED
    -0.51
    tencent
    -0.51
    tyfik
    -0.50
     tricky
    -0.50
     lidi
    -0.48
    Subview
    -0.48
     
    -0.48
     vindicated
    -0.47
    itch
    -0.47
    POSITIVE LOGITS
     reasonable
    1.09
     reaſon
    1.04
    reasonable
    1.02
    Reasonable
    1.00
     raisonnable
    0.99
     Reasonable
    0.96
     reasonably
    0.95
    reasonably
    0.90
     itſelf
    0.90
     razonable
    0.88
    Activations Density 1.415%

    No Known Activations