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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 10474
    Prev
    Next
    INDEX
    Explanations

    words that indicate the initiation of actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 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
    detectChanges
    -0.73
     Cientí
    -0.70
     crainte
    -0.69
     économiques
    -0.66
     définiti
    -0.65
     auroit
    -0.65
     vectorielles
    -0.64
     vœux
    -0.64
     saada
    -0.64
     Jefus
    -0.63
    POSITIVE LOGITS
     beginning
    1.01
     begin
    0.98
    beginning
    0.86
     commence
    0.83
     commencing
    0.77
     начина
    0.74
     beginnen
    0.73
     starting
    0.72
     beginnings
    0.71
     Beginning
    0.70
    Activations Density 0.193%

    No Known Activations