© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 563
    Prev
    Next
    INDEX
    Explanations

    terms related to installation and infrastructure

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

    technical terms related to infrastructure and utility management

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

    utility, sanitation, supply infrastructure

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ScopeManager
    -0.56
    DeleteBehavior
    -0.51
    oriasis
    -0.49
     שוליים
    -0.48
    unhofer
    -0.47
     celo
    -0.47
    usercontent
    -0.47
    ffffff
    -0.46
     препратки
    -0.46
    RefreshLayout
    -0.45
    POSITIVE LOGITS
     utilities
    1.21
     sewer
    1.19
     infrastructure
    1.18
     pipes
    1.17
     pipelines
    1.14
     Utilities
    1.07
     utility
    1.05
     infrastructures
    1.05
     pipeline
    1.04
     sewers
    1.04
    Activations Density 0.127%

    No Known Activations