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. 7378
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns and possessive forms

    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
    jména
    -0.50
    Ошибка
    -0.49
    적으로
    -0.48
    ciri
    -0.46
     okazji
    -0.45
     vian
    -0.45
    jší
    -0.45
    koop
    -0.43
    uny
    -0.43
    逊
    -0.43
    POSITIVE LOGITS
    InjectAttribute
    1.13
     ostavi
    0.98
    verwijspagina
    0.95
    UnsafeEnabled
    0.93
     createSlice
    0.91
    лтемелер
    0.90
    __':
    0.89
    __':
    
    0.86
     nakalista
    0.86
     surla
    0.86
    Activations Density 0.649%

    No Known Activations