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

    Neuronpedia

    Jacobian LensNEW
    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. 16378
    Prev
    Next
    INDEX
    Explanations

    references to complex or complicated structures, concepts, or phenomena

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

    Preceding "ified", "structure", or "complex"

    np_acts-logits-general · gemini-2.0-flash

    complexified structures and concepts

    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
     AssemblyTitle
    -1.11
    OGND
    -0.87
     INTERESAR
    -0.84
    styleUrls
    -0.82
    serviceWorker
    -0.82
    脚注の使い方
    -0.81
    ManagedBean
    -0.79
     Audiodateien
    -0.79
    enterOuterAlt
    -0.79
    MessageOf
    -0.79
    POSITIVE LOGITS
    ed
    0.81
    XmlAccessType
    0.77
    ation
    0.66
    ing
    0.57
    ED
    0.55
    xes
    0.54
    ities
    0.54
    et
    0.53
    minded
    0.52
    es
    0.50
    Activations Density 0.064%

    No Known Activations