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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7711
    Prev
    Next
    INDEX
    Explanations

    references to the Resident Evil game, and specifically the characters Leon, Link, Saddler, and Resident Evil 4.

    oai_token-act-pair · gemini-2.0-flash

    Link (video game)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     muka
    -0.43
    routs
    -0.43
    ArgsConstructor
    -0.41
    장
    -0.40
    artes
    -0.39
     pol
    -0.39
    uming
    -0.38
     van
    -0.37
    ANDA
    -0.37
    ⎧
    -0.36
    POSITIVE LOGITS
    Xna
    1.03
     muualla
    0.89
    ValueStyle
    0.88
    Portail
    0.88
     CreateTagHelper
    0.88
     kasarigan
    0.85
     Roskov
    0.83
    ंदीखरीदारी
    0.79
    icoot
    0.79
     سكانية
    0.77
    Activations Density 0.648%

    No Known Activations