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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 25-GEMMASCOPE-RES-16K
    6. 8671
    Prev
    Next
    INDEX
    Explanations

    terms related to programming patterns, particularly those involving resource management and data handling in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     now
    -0.86
     THIS
    -0.77
     when
    -0.77
     AND
    -0.74
     after
    -0.73
     TO
    -0.73
     next
    -0.72
     FOR
    -0.72
     since
    -0.71
     then
    -0.70
    POSITIVE LOGITS
     parlour
    0.65
     metallurgical
    0.65
     scienti
    0.65
     StatefulWidget
    0.64
     manifesto
    0.64
     neuroscience
    0.64
     synergies
    0.63
     repatriation
    0.63
     galley
    0.62
     syndicate
    0.62
    Activations Density 0.419%

    No Known Activations