© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7408
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dump" and the concept of "lifetime."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     occupé
    -0.71
     تانيه
    -0.67
     debout
    -0.66
     décé
    -0.64
    wapV
    -0.62
     privées
    -0.61
     détru
    -0.61
     exécut
    -0.61
     défend
    -0.59
    ActivityCompat
    -0.59
    POSITIVE LOGITS
     selective
    0.93
     sele
    0.86
     Sele
    0.81
     dump
    0.75
     selec
    0.74
    Selective
    0.71
     selection
    0.69
     Selective
    0.69
    <thead>
    0.68
    selective
    0.66
    Activations Density 0.129%

    No Known Activations