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. 12-GEMMASCOPE-RES-16K
    6. 10076
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    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
    -0.84
     itſelf
    -0.73
     NDEBUG
    -0.70
    pośred
    -0.66
    ation
    -0.65
    Switcher
    -0.63
     ilma
    -0.63
     sonne
    -0.62
    fisher
    -0.60
     abel
    -0.60
    POSITIVE LOGITS
     TO
    1.24
     to
    1.23
     zu
    1.02
     To
    1.00
    TO
    1.00
    To
    0.98
    scrollTo
    0.94
    AddTagHelper
    0.90
     να
    0.90
    yto
    0.90
    Activations Density 1.170%

    No Known Activations