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. 16170
    Prev
    Next
    INDEX
    Explanations

    mentions of a Wicklow Mountains race, including locations and people

    oai_token-act-pair · gemini-2.0-flash

    Irish/Ireland

    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
    RegressionTest
    -0.55
    almaz
    -0.47
     Bever
    -0.46
     Khart
    -0.44
     Scotland
    -0.42
     picioare
    -0.41
     intptr
    -0.40
    iczny
    -0.40
     enfri
    -0.40
     Scottish
    -0.40
    POSITIVE LOGITS
     Irish
    0.86
    Irish
    0.75
     Dublin
    0.74
     Ireland
    0.73
     irish
    0.68
    Ireland
    0.68
    Dublin
    0.68
    Irlande
    0.65
     Dara
    0.64
    fromCharCode
    0.64
    Activations Density 0.457%

    No Known Activations