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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 665
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to a person and their involvement in an activity (e.g., "her operation" or "his campaign")

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ostavi
    -0.75
    CopyWith
    -0.65
     nahilalakip
    -0.65
     StatefulWidget
    -0.63
    afficheront
    -0.58
    expandindo
    -0.57
     protoimpl
    -0.57
    RegistryLite
    -0.57
    Serde
    -0.57
    nocache
    -0.56
    POSITIVE LOGITS
    helves
    0.63
    TagMode
    0.61
    SerializedName
    0.57
     Staff
    0.53
    ++]=
    0.52
     ++)
    0.51
    nissen
    0.51
    település
    0.51
    ]").
    0.49
    ?",
    0.49
    Activations Density 28.985%

    No Known Activations