© 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. 16-GEMMASCOPE-RES-16K
    11. 3794
    Prev
    Next
    INDEX
    Explanations

    instances of the word "had" to indicate past experiences or actions

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

    Follows "had"

    np_acts-logits-general · gemini-2.0-flash

    past experiences or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    woordig
    -0.73
    GRAN
    -0.68
     Mathi
    -0.66
     Pter
    -0.65
     Selena
    -0.65
     publiques
    -0.64
     Ressources
    -0.63
     Olms
    -0.63
     Teut
    -0.62
    PreferredItem
    -0.62
    POSITIVE LOGITS
     hoped
    1.06
     earlier
    0.94
     originalmente
    0.89
    Earlier
    0.85
     originally
    0.84
     HAD
    0.82
     previously
    0.81
     Earlier
    0.81
     had
    0.79
     ursprünglich
    0.79
    Activations Density 0.148%

    No Known Activations