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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1124
    Prev
    Next
    INDEX
    Explanations

    possessive nouns and pronouns in the third person

    oai_token-act-pair · gemini-2.0-flash

    '[word]s' possessive form. Note: This is more of a technical neuron, as opposed to semantic

    np_token-act-pair-logits · gemini-2.0-flash

    relationships between people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    IonicModule
    -0.49
    ext
    -0.47
    atra
    -0.44
    hasMoreElements
    -0.43
    ئيس
    -0.41
    Zie
    -0.38
    WriteTagHelper
    -0.38
    SharedCtor
    -0.38
    OGND
    -0.37
    CopyWith
    -0.37
    POSITIVE LOGITS
    новништво
    0.62
    ScopeManager
    0.61
    !*\
    0.61
     heapq
    0.60
    esterday
    0.60
     Territorial
    0.59
    Geplaatst
    0.57
    antwoorden
    0.57
     territorial
    0.57
     geograph
    0.57
    Activations Density 0.990%

    No Known Activations