© 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. 30-GEMMASCOPE-RES-16K
    11. 12475
    Prev
    Next
    INDEX
    Explanations

    lines of code related to conditional structures and closing brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or special characters

    np_acts-logits-general · gemini-2.0-flash

    documentation and code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     venganza
    -0.42
     Dusche
    -0.39
     novio
    -0.38
     locura
    -0.38
     votación
    -0.37
     figlio
    -0.37
     explosión
    -0.37
     tramonto
    -0.36
     parlando
    -0.35
     identidad
    -0.35
    POSITIVE LOGITS
    :✨
    0.95
    Datuak
    0.75
    /*
    0.73
     lenker
    0.72
    expandindo
    0.71
    endregion
    0.68
     Infórmanos
    0.66
     Administrativna
    0.66
    存于互联网档案馆
    0.63
     Italijanski
    0.63
    Activations Density 0.410%

    No Known Activations