© 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. 27-GEMMASCOPE-RES-16K
    11. 9538
    Prev
    Next
    INDEX
    Explanations

    the occurrence and variations of the word "come" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infór
    -0.48
     utilización
    -0.45
     prevención
    -0.44
     Anfitrión
    -0.42
     Leidenschaft
    -0.41
     Mehrheit
    -0.41
     atracción
    -0.40
     legislación
    -0.40
     transparencia
    -0.40
     actualidad
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.65
    IsContent
    0.61
     createState
    0.57
    comes
    0.55
     Comes
    0.54
    equipped
    0.54
     createSlice
    0.54
     NSCoder
    0.53
    Comes
    0.53
     comes
    0.52
    Activations Density 0.099%

    No Known Activations