© 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. 20-GEMMASCOPE-RES-16K
    11. 6922
    Prev
    Next
    INDEX
    Explanations

    references to universities and academic institutions

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

    Universities (e.g., Mellon, Duke, Princeton, Stanford)

    np_acts-logits-general · gemini-2.0-flash

    university names followed by University

    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
    ItemGroup
    -0.53
    FAQs
    -0.49
    են
    -0.45
    jure
    -0.45
    ertor
    -0.44
    gout
    -0.43
    ղ
    -0.43
     tab
    -0.42
    stva
    -0.42
     ст
    -0.42
    POSITIVE LOGITS
     University
    1.87
    University
    1.55
     UNIVERSITY
    1.50
     university
    1.49
     Univ
    1.28
     Univer
    1.25
    university
    1.24
    UNIVERSITY
    1.20
     Üniversitesi
    1.19
     Universite
    1.10
    Activations Density 0.122%

    No Known Activations