© 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. 3595
    Prev
    Next
    INDEX
    Explanations

    terms related to file and directory manipulations in a programming context

    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
     createState
    -0.56
     Scopus
    -0.55
    unsplash
    -0.55
     FetchType
    -0.55
     unknownFields
    -0.53
    hopper
    -0.53
     SqlCommand
    -0.51
    waitKey
    -0.51
    ">//
    -0.51
    setVerticalGroup
    -0.50
    POSITIVE LOGITS
    DirPath
    0.64
    dirname
    0.62
    mkdir
    0.59
    Dirs
    0.59
     mkdir
    0.58
    SpringBootTest
    0.58
    ImageField
    0.58
    PDIR
    0.57
    pushd
    0.56
    RootPath
    0.55
    Activations Density 0.344%

    No Known Activations