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. 10019
    Prev
    Next
    INDEX
    Explanations

    pronouns and their usage in context

    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
    httphttps
    -0.79
    UnusedPrivate
    -0.77
     Reſ
    -0.75
     Diſ
    -0.75
     Middletown
    -0.75
     pleaſure
    -0.74
    Abr
    -0.72
     cauſe
    -0.72
     Anſ
    -0.71
     fevere
    -0.71
    POSITIVE LOGITS
     them
    0.72
     it
    0.72
    éndolo
    0.67
    doit
    0.65
     him
    0.64
     initComponents
    0.61
    MessageTagHelper
    0.61
     usarlo
    0.58
     himo
    0.57
     THEM
    0.57
    Activations Density 0.174%

    No Known Activations