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. 13696
    Prev
    Next
    INDEX
    Explanations

    statements regarding consequences and societal beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     tromper
    -0.51
     altså
    -0.48
     alturas
    -0.48
     nourrir
    -0.47
     tider
    -0.46
     vitales
    -0.45
     saluti
    -0.45
     laiko
    -0.45
     recevrez
    -0.45
    とはいえ
    -0.44
    POSITIVE LOGITS
    Personensuche
    1.07
    uxxxx
    1.03
    TypedDataSet
    1.01
    出版年
    0.98
    LookAnd
    0.76
    StoryboardSegue
    0.76
    تقاوى
    0.75
     AssemblyProduct
    0.75
    webElementXpaths
    0.74
     Италијани
    0.74
    Activations Density 0.240%

    No Known Activations