© 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. 0-GEMMASCOPE-RES-16K
    11. 15037
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "inline" and conjunctions or negatives like "nor"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    berdayakan
    -0.77
    ementara
    -0.76
     Grüsse
    -0.75
    jména
    -0.75
     desmotivaciones
    -0.74
    gucig
    -0.73
     ujednoznacz
    -0.71
    genodigd
    -0.67
    pulseira
    -0.66
    ßerdem
    -0.66
    POSITIVE LOGITS
     
    0.57
    <strong>
    0.57
    ↵↵
    0.55
      
    0.54
    (
    0.47
     Labour
    0.46
    ↵
    0.46
    <em>
    0.46
    Â
    0.44
    2
    0.44
    Activations Density 0.380%

    No Known Activations