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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6831
    Prev
    Next
    INDEX
    Explanations

    instances of the words "It Is" or "In", and also SQL "SELECT" statements, suggesting it is capturing importance or selection within a dataset potentially related to medical information or other structured data

    oai_token-act-pair · gemini-2.0-flash

    structured documents/formal texts

    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
    GEBURTSDATUM
    -1.23
    parsedMessage
    -1.20
    principalTable
    -1.04
    +#+#
    -1.00
    complexContent
    -0.98
    richTextPanel
    -0.95
    rrggbb
    -0.90
    tagHelperRunner
    -0.88
    etheless
    -0.85
    sidemargin
    -0.85
    POSITIVE LOGITS
    quele
    0.56
    OrFail
    0.56
    vänd
    0.56
    lapping
    0.55
    一方
    0.49
    CFLAGS
    0.48
    inafter
    0.48
    IAm
    0.45
    reciated
    0.44
    érience
    0.44
    Activations Density 28.976%

    No Known Activations