© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15008
    Prev
    Next
    INDEX
    Explanations

    connections to roots, culture, and foundational elements across various contexts

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

    "root" and origins

    np_acts-logits-general · gemini-2.0-flash

    origins and foundations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.68
     Waray
    -0.65
     AssemblyTitle
    -0.64
    出版年
    -0.58
    MemoryWarning
    -0.57
     MonoBehaviour
    -0.56
     @"/
    -0.56
    verwijspagina
    -0.55
    Referencer
    -0.55
    তথ্যসূত্র
    -0.54
    POSITIVE LOGITS
     roots
    1.70
     root
    1.57
     rooted
    1.50
     Roots
    1.39
    roots
    1.39
    rooted
    1.38
    root
    1.33
     ROOT
    1.30
     Root
    1.29
    Roots
    1.28
    Activations Density 0.224%

    No Known Activations