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. 25-GEMMASCOPE-RES-16K
    6. 12477
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs related to table views and data handling in mobile app development

    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
     >=",
    -0.58
    makeText
    -0.52
    setDo
    -0.50
     domini
    -0.49
     dominion
    -0.49
    Domin
    -0.48
     ilu
    -0.47
     reflex
    -0.46
     Dodson
    -0.46
     domin
    -0.45
    POSITIVE LOGITS
    IndexPath
    0.91
     indexPath
    0.90
    Section
    0.88
     Section
    0.86
     section
    0.86
    InSection
    0.84
    section
    0.83
     sections
    0.81
     IndexPath
    0.78
    indexPath
    0.78
    Activations Density 0.158%

    No Known Activations