© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13380
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated operations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "+" followed by "function" in code

    np_acts-logits-general · gemini-2.0-flash

    function definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -1.20
     ExecuteAsync
    -1.02
    setVerticalGroup
    -0.89
    haikusbot
    -0.86
    sizeCache
    -0.81
     typelib
    -0.81
     Infórmanos
    -0.77
     propOrder
    -0.77
    下载附件
    -0.76
     AssemblyCompany
    -0.75
    POSITIVE LOGITS
     the
    0.59
    ,
    0.55
    _
    0.55
    [toxicity=0]
    0.55
    -
    0.54
     
    0.53
    )
    0.49
    :
    0.47
     of
    0.46
     -
    0.45
    Activations Density 0.305%

    No Known Activations