© 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. 8-GEMMASCOPE-RES-16K
    11. 10709
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "Da" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.98
    specialchars
    -0.86
    Vog
    -0.85
    getLog
    -0.84
     themſelves
    -0.82
     Segura
    -0.82
    httphttps
    -0.82
     Pegasus
    -0.81
     AssemblyVersion
    -0.80
     Vogt
    -0.79
    POSITIVE LOGITS
     Da
    1.35
    Da
    1.24
     da
    1.18
     DA
    1.14
    DA
    0.98
    da
    0.86
     daisies
    0.80
     DAZ
    0.79
    Vinci
    0.79
    Daemon
    0.77
    Activations Density 0.086%

    No Known Activations