© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27183
    Prev
    Next
    INDEX
    Explanations

    arrow functions and their syntax in programming, particularly in JavaScript

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

    months) or my microphone)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.48
     Sort
    -0.48
     speaking
    -0.48
     withal
    -0.48
    ortunadamente
    -0.47
    ี่ยม
    -0.47
     canina
    -0.47
     kohta
    -0.45
    atoday
    -0.45
     Servlet
    -0.45
    POSITIVE LOGITS
    WriteBarrier
    0.82
    ⓧ
    0.78
    Vidite
    0.77
    WireFormatLite
    0.76
     Préférences
    0.73
     uska
    0.72
    IndentedString
    0.71
    UserScript
    0.70
     Infórmanos
    0.70
    /**
    0.70
    Activations Density 0.010%

    No Known Activations