© 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. 11-GEMMASCOPE-RES-16K
    11. 4629
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency or patterns of regular occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.57
     utafitiHapana
    -0.57
    XmlAccessorType
    -0.56
    MockBean
    -0.55
    ValueStyle
    -0.54
     AIRCRAFT
    -0.53
    berdayakan
    -0.52
    IntoConstraints
    -0.52
     GenerationType
    -0.51
    Aluminium
    -0.51
    POSITIVE LOGITS
     regular
    1.73
    regular
    1.72
    Regular
    1.68
     Regular
    1.62
     REGULAR
    1.53
     regularly
    1.52
    REGULAR
    1.45
     Regularly
    1.39
     regulares
    1.33
     régulier
    1.22
    Activations Density 0.163%

    No Known Activations