© 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. 14729
    Prev
    Next
    INDEX
    Explanations

    references to JSON and file operations in code

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

    Code block endings or closures

    np_acts-logits-general · gemini-2.0-flash

    ending or concluding

    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
    featureID
    -0.90
    XmlAccessType
    -0.81
     ExecuteAsync
    -0.81
    __(/*!
    -0.81
     AssemblyTitle
    -0.64
    таратура
    -0.60
     AssemblyProduct
    -0.60
    ValueGeneration
    -0.60
    üyada
    -0.60
    endphp
    -0.59
    POSITIVE LOGITS
     ends
    0.73
     concludes
    0.72
     closing
    0.71
     concluye
    0.68
     end
    0.67
     closes
    0.65
     finished
    0.65
     finish
    0.64
     conclude
    0.64
     conclusion
    0.63
    Activations Density 0.259%

    No Known Activations