© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6438
    Prev
    Next
    INDEX
    Explanations

    references to user interface components and data structures in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     habido
    -0.35
     sanitarias
    -0.34
     prêtre
    -0.34
    Personendaten
    -0.34
     particulières
    -0.33
     Aufwand
    -0.32
     pauvres
    -0.32
    rantz
    -0.32
    Interpretation
    -0.32
     étrangères
    -0.32
    POSITIVE LOGITS
    dataGridView
    0.79
    tabPage
    0.77
    pictureBox
    0.75
    crollView
    0.74
     tableView
    0.73
     dataGridView
    0.73
     pictureBox
    0.72
    listView
    0.72
    ings
    0.70
     GridView
    0.69
    Activations Density 1.301%

    No Known Activations