© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6810
    Prev
    Next
    INDEX
    Explanations

    functions and properties related to data management in programming contexts

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

    CSS selectors or related web syntax

    np_acts-logits-general · gemini-2.0-flash

    CSS selectors

    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
     AssemblyCompany
    -0.92
    Portale
    -0.82
    AnimationsModule
    -0.76
     NDEBUG
    -0.76
     DBNull
    -0.75
    detectChanges
    -0.74
    isContained
    -0.71
     CURIAM
    -0.70
    openConnection
    -0.70
    findpost
    -0.69
    POSITIVE LOGITS
     flexible
    0.57
     functionality
    0.52
    灵活
    0.51
     flexível
    0.51
     use
    0.50
     deprecated
    0.50
     feature
    0.49
     syntax
    0.49
     default
    0.48
     allows
    0.48
    Activations Density 1.362%

    No Known Activations