© 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. 6386
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "de" and its variants

    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
    mybatisplus
    -0.94
     Theſe
    -0.93
    NameInMap
    -0.89
    RunWith
    -0.88
    WebVitals
    -0.85
    ')")
    -0.84
    fycat
    -0.83
    InitVars
    -0.83
     سكانية
    -0.82
    OGND
    -0.82
    POSITIVE LOGITS
    De
    1.27
     De
    1.20
     de
    1.12
    de
    1.04
    DE
    1.02
     DE
    0.97
     де
    0.82
     DeV
    0.76
     deg
    0.76
    デ
    0.72
    Activations Density 0.127%

    No Known Activations