© 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. 5-GEMMASCOPE-RES-16K
    11. 3130
    Prev
    Next
    INDEX
    Explanations

    code pragmas and compiler directives

    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
     PLWABN
    -0.69
    contentLoaded
    -0.65
    ContentAsync
    -0.60
    ftagPool
    -0.58
    andExpect
    -0.58
    原始内容存档于
    -0.56
    Edge
    -0.56
    swift
    -0.55
    !*\
    -0.55
    MeasureSpec
    -0.54
    POSITIVE LOGITS
     [*]
    1.62
    addContainerGap
    1.47
    pragma
    1.46
    :✨
    1.21
    AndEndTag
    1.03
    DateTimeField
    0.94
     >=",
    0.82
    endregion
    0.79
     cellspacing
    0.78
    ragma
    0.74
    Activations Density 0.059%

    No Known Activations