© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 12929
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and processes 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 @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.81
     '\\;'
    -0.79
    __':
    -0.79
    ✨:
    -0.76
    FunctionFlags
    -0.76
     lenker
    -0.76
     שוליים
    -0.72
     autorytatywna
    -0.70
    ValueStyle
    -0.69
    ClientRect
    -0.69
    POSITIVE LOGITS
     resourceCulture
    0.52
    GenerationType
    0.51
     reconoci
    0.42
    的形式
    0.39
    seamnă
    0.38
     censi
    0.38
    field
    0.38
     neki
    0.37
    commodation
    0.37
    chism
    0.37
    Activations Density 1.165%

    No Known Activations