Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10282
    Prev
    Next
    INDEX
    Explanations

    the word "his" or "its" near verbs, especially in the context of sports or medical treatments.

    oai_token-act-pair · gemini-2.0-flash

    ordinal numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     once
    -1.56
    once
    -1.44
     forever
    -1.37
    Once
    -1.31
     Once
    -1.27
     ONCE
    -1.22
    forever
    -1.21
    ONCE
    -1.21
     Forever
    -1.20
     FOREVER
    -1.13
    POSITIVE LOGITS
     ninth
    0.79
     tenth
    0.73
     eighth
    0.72
    RSpec
    0.71
     Tenth
    0.71
    tvguidetime
    0.71
     thirteenth
    0.70
     fourteenth
    0.69
     seventh
    0.68
     eleventh
    0.66
    Activations Density 0.787%

    No Known Activations