© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 3500
    Prev
    Next
    INDEX
    Explanations

    references to "bottom line" or similar phrases indicating financial conclusions or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.89
     onAnimation
    -0.77
    KURZBESCHREIBUNG
    -0.72
     HttpNotFound
    -0.71
     Réponses
    -0.69
     ویکی‌پدیا
    -0.68
    NewUrlParser
    -0.68
    setViewportView
    -0.67
    riezmann
    -0.67
    AccessorTable
    -0.67
    POSITIVE LOGITS
     Bottom
    0.80
     botto
    0.79
    bottom
    0.75
     BOTTOM
    0.74
     bottom
    0.74
     bottoms
    0.74
     Onder
    0.72
     ↓
    0.69
     marginBottom
    0.69
     baix
    0.65
    Activations Density 0.163%

    No Known Activations