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. 0-GEMMASCOPE-RES-16K
    6. 91
    Prev
    Next
    INDEX
    Explanations

    terms related to glowing or luminous objects and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.71
    principalTable
    -0.68
    MIDDLEWARE
    -0.66
     Nicosia
    -0.60
    rolid
    -0.59
    zyż
    -0.58
     שוליים
    -0.57
     Perseus
    -0.56
    براير
    -0.55
     pressão
    -0.55
    POSITIVE LOGITS
     glow
    1.09
     shine
    1.05
     shining
    1.05
     shines
    0.95
     glows
    0.93
     luminous
    0.92
     Glow
    0.90
    glow
    0.89
     Shine
    0.88
     sparkle
    0.87
    Activations Density 3.091%

    No Known Activations