© 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. 9084
    Prev
    Next
    INDEX
    Explanations

    connections between interactions, experiences, and contexts in various scenarios

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

    Prepositions followed by articles

    np_acts-logits-general · gemini-2.0-flash

    determinado / determinada / someone

    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
    CodeDom
    -0.61
     مرئيه
    -0.57
    FormTagHelper
    -0.53
    protoimpl
    -0.52
     diesmal
    -0.52
    insertBefore
    -0.51
     androidx
    -0.50
    次第
    -0.50
    isielt
    -0.49
     Metropolitana
    -0.48
    POSITIVE LOGITS
     suatu
    1.30
     someone
    1.17
     seseorang
    1.14
     sebuah
    1.08
    someone
    1.02
     somebody
    1.01
    某个
    1.00
     determinado
    0.96
     determinada
    0.95
    Someone
    0.94
    Activations Density 1.176%

    No Known Activations