Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1601
    Prev
    Next
    INDEX
    Explanations

    specific operators and indicators within programming or theoretical frameworks

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

    Code, programming, or technical language

    np_acts-logits-general · gemini-2.0-flash

    Antonio Armijoparadigm shiftmissing directivewingless-related integrationaround-the-clock serviceobservance of procedure

    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
    ,
    -0.43
    Referensi
    -0.42
    .
    -0.42
     eux
    -0.41
     nesta
    -0.38
    ึง
    -0.38
    ற்ற
    -0.37
     one
    -0.37
    しく
    -0.37
    setContentView
    -0.37
    POSITIVE LOGITS
    Hentet
    0.97
    ")){
    
    0.97
     disambiguazione
    0.96
     ModelExpression
    0.96
    adaptiveStyles
    0.95
    AddTagHelper
    0.95
    OGND
    0.93
    imetsu
    0.91
     يتيمه
    0.89
    }}}
    
    0.89
    Activations Density 1.159%

    No Known Activations