© 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. 962
    Prev
    Next
    INDEX
    Explanations

    references to structures, systems, or models composed of components or layers

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

    "Made up of" or "composed of"

    np_acts-logits-general · gemini-2.0-flash

    made up of

    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
    出版年
    -0.79
    Tikang
    -0.75
    nadier
    -0.55
     Biôgrafia
    -0.54
    saraba
    -0.54
    executeUpdate
    -0.54
    たまた
    -0.54
     Мексичка
    -0.54
     pollut
    -0.54
    CodeAttribute
    -0.52
    POSITIVE LOGITS
     consisting
    2.69
     consists
    2.64
     composed
    2.49
     comprised
    2.44
     consisted
    2.42
     consist
    2.40
     comprising
    2.21
     comprises
    2.15
     terdiri
    2.11
    composed
    2.03
    Activations Density 0.793%

    No Known Activations