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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2524
    Prev
    Next
    INDEX
    Explanations

    elements related to API error handling and response structures

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

    Code keywords (val, const, let)

    np_acts-logits-general · gemini-2.0-flash

    variable declarations and assignments

    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
     courseId
    -0.55
    dataclass
    -0.51
     společnost
    -0.50
    GeneratedMessage
    -0.49
     colorWith
    -0.48
     UIColor
    -0.47
     eventName
    -0.47
     postId
    -0.46
     Audiodateien
    -0.46
     enctype
    -0.46
    POSITIVE LOGITS
     new
    0.92
     temp
    0.92
     result
    0.92
     temporary
    0.85
     old
    0.84
     actual
    0.83
     original
    0.83
     current
    0.79
     potential
    0.77
     local
    0.75
    Activations Density 0.266%

    No Known Activations