© 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. 10-GEMMASCOPE-RES-16K
    11. 16330
    Prev
    Next
    INDEX
    Explanations

    components or attributes related to a shared common framework or library

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.84
     StatefulWidget
    -0.83
    routeProvider
    -0.76
    SourceChecksum
    -0.76
    AddWithValue
    -0.73
    Personensuche
    -0.72
    CreateMap
    -0.71
     GetEnumerator
    -0.71
    stateProvider
    -0.68
    ArgsConstructor
    -0.67
    POSITIVE LOGITS
    ところで
    0.57
    Common
    0.55
    通用
    0.53
    common
    0.53
    misc
    0.53
    basic
    0.51
     básicos
    0.50
     Allgemeinen
    0.50
     通用
    0.50
    CELLANEOUS
    0.49
    Activations Density 0.261%

    No Known Activations