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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14460
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'I' or 'it', sometimes along with nearby auxiliary verbs or pronouns.

    oai_token-act-pair · gemini-2.0-flash

    personal narratives and opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     even
    -1.41
    even
    -1.27
    Even
    -1.10
     EVEN
    -1.06
    EVEN
    -1.02
     Even
    -1.02
     даже
    -0.96
     bahkan
    -0.95
     навіть
    -0.91
     persino
    -0.90
    POSITIVE LOGITS
    MigrationBuilder
    0.84
     estekak
    0.72
    awtextra
    0.57
     "..\..\..\
    0.56
    bewerken
    0.56
     gynhyrchwyd
    0.55
    تقاوى
    0.54
    ContentAsync
    0.51
     certainly
    0.50
    modelBuilder
    0.50
    Activations Density 4.171%

    No Known Activations