© 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. 1-GEMMASCOPE-RES-16K
    11. 6315
    Prev
    Next
    INDEX
    Explanations

    instances of the word "caught" in relation to legal or personal situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.73
    jspx
    -0.72
    basicConfig
    -0.71
    Geplaatst
    -0.67
     CreateTagHelper
    -0.65
     commas
    -0.64
    zzleHttp
    -0.64
     оригіналу
    -0.63
     AssemblyCulture
    -0.63
    יבה
    -0.63
    POSITIVE LOGITS
     invasion
    0.96
     caught
    0.93
    caught
    0.91
     Caught
    0.89
    invasion
    0.85
     invaded
    0.78
     invading
    0.77
     invasions
    0.75
    Caught
    0.71
     Invasion
    0.70
    Activations Density 0.051%

    No Known Activations