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. 5-GEMMASCOPE-RES-16K
    6. 2649
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "I."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -1.21
    Datuak
    -1.10
     autorytatywna
    -1.08
    rungsseite
    -1.07
     HttpNotFound
    -1.07
     وتسجيلات
    -1.04
     Efq
    -1.02
     ModelExpression
    -1.01
    mybatisplus
    -1.01
     ujednoznacz
    -0.99
    POSITIVE LOGITS
    I
    1.32
     I
    1.06
    We
    1.00
    It
    0.94
    The
    0.92
    In
    0.89
     
    0.87
     We
    0.86
     It
    0.81
    You
    0.78
    Activations Density 0.129%

    No Known Activations