© 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
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4171
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ma" and variations of the theme of exploitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppuden
    -0.56
     initComponents
    -0.45
     مشين
    -0.45
    rungsseite
    -0.44
     Serikat
    -0.44
    unref
    -0.43
    ChildScrollView
    -0.42
    chartInstance
    -0.42
    Bronnen
    -0.42
    WireFormatLite
    -0.42
    POSITIVE LOGITS
     pun
    0.95
     Pun
    0.89
     exploit
    0.88
    Pun
    0.88
    pun
    0.85
     PUN
    0.84
    ma
    0.83
     lease
    0.72
     penalty
    0.70
     punishment
    0.70
    Activations Density 0.310%

    No Known Activations