Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 840
    Prev
    Next
    INDEX
    Explanations

    structured data formats and serialization functions in programming contexts

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

    Code snippets related to JSON or Swift

    np_acts-logits-general · gemini-2.0-flash

    JSON serialization and validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chok
    -0.51
     hostages
    -0.50
    ingtones
    -0.50
    PathVariable
    -0.49
     Controlling
    -0.48
     TimeUnit
    -0.48
    AspNet
    -0.47
    handlung
    -0.47
     HomeController
    -0.45
    ertale
    -0.45
    POSITIVE LOGITS
     serialized
    0.76
     JSON
    0.70
     json
    0.69
     serialization
    0.69
    json
    0.66
    JSON
    0.64
    Serialize
    0.64
    序列化
    0.64
    AccessorTable
    0.61
    serial
    0.61
    Activations Density 0.591%

    No Known Activations