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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10464
    Prev
    Next
    INDEX
    Explanations

    discussions of needs and demands related to healthcare, particularly regarding patients with specific conditions like DMD

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.60
    scalatest
    -0.59
    الدراسه
    -0.57
    tonsoft
    -0.55
     precau
    -0.54
    юрпри
    -0.54
    QMetaType
    -0.54
     AssemblyProduct
    -0.51
     precautions
    -0.51
     precaution
    -0.51
    POSITIVE LOGITS
     lack
    1.03
    亟
    1.00
     lacking
    0.98
    Lack
    0.95
     lacked
    0.94
     inadequ
    0.92
     needs
    0.91
     Lack
    0.91
     frustration
    0.90
     lacks
    0.90
    Activations Density 0.463%

    No Known Activations