© 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. 15-GEMMASCOPE-RES-16K
    11. 3244
    Prev
    Next
    INDEX
    Explanations

    phrases that express engagement and interaction with the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     once
    -0.49
     ap
    -0.47
     наме
    -0.43
    Os
    -0.42
     os
    -0.40
    iden
    -0.40
     hors
    -0.40
    EnableWeb
    -0.39
     you
    -0.39
     sao
    -0.39
    POSITIVE LOGITS
     conmigo
    1.50
     comigo
    1.21
    endphp
    0.89
     моих
    0.88
    UnusedPrivate
    0.86
    AddTagHelper
    0.85
     miei
    0.85
     mnie
    0.84
     मेरे
    0.83
     meines
    0.83
    Activations Density 0.233%

    No Known Activations