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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9363
    Prev
    Next
    INDEX
    Explanations

    numerical values related to data coding or programming contexts

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

    Code, software, version numbers, and programming files

    np_acts-logits-general · gemini-2.0-flash

    package management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meaningful
    -0.49
    modb
    -0.47
     Planner
    -0.47
    //</
    -0.47
    ModelBuilder
    -0.45
    SharedDtor
    -0.45
     planner
    -0.45
    xaml
    -0.44
    udian
    -0.44
    Manus
    -0.44
    POSITIVE LOGITS
    npmjs
    0.78
    yarnpkg
    0.76
     getVersion
    0.73
     BorderSide
    0.73
     installed
    0.72
     uninstalled
    0.71
     packageName
    0.69
     installs
    0.67
     vendors
    0.67
     libraries
    0.65
    Activations Density 0.561%

    No Known Activations