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. 5-GEMMASCOPE-RES-16K
    6. 9397
    Prev
    Next
    INDEX
    Explanations

    references to global variables in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.72
    aarrggbb
    -0.66
     ""],
    -0.65
     SwiftUI
    -0.65
     Jefus
    -0.64
     sleigh
    -0.63
    TSCA
    -0.61
     ―――――
    -0.61
    rungsseite
    -0.60
     rupees
    -0.60
    POSITIVE LOGITS
     global
    1.41
    global
    1.39
    Global
    1.11
     Global
    1.08
     globally
    1.01
     GLOBAL
    0.99
     globales
    0.98
     globale
    0.97
    GLOBAL
    0.97
    全局
    0.89
    Activations Density 0.020%

    No Known Activations