© 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. 21-GEMMASCOPE-RES-16K
    11. 14364
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -1.03
     defaultstate
    -0.76
     AssemblyCulture
    -0.76
    ScopeManager
    -0.75
     تضيفلها
    -0.72
    AccessorTable
    -0.72
    NameInMap
    -0.71
     AssemblyCompany
    -0.71
    tagHelper
    -0.69
    quias
    -0.68
    POSITIVE LOGITS
     to
    3.04
     kepada
    1.70
    到
    1.45
    tothe
    1.44
    to
    1.24
     unto
    1.23
     vnto
    1.22
     إلى
    1.15
     thereto
    1.10
     به
    1.02
    Activations Density 3.188%

    No Known Activations