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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7157
    Prev
    Next
    INDEX
    Explanations

    titles, particularly those with the word "The" in them, or words related to black people

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.11
    RegressionTest
    -0.66
    ')):
    -0.65
    "}>
    -0.59
    '):
    
    -0.59
    $")
    -0.58
    ")){
    
    -0.57
     nemlig
    -0.57
    Guys
    -0.57
    '})
    -0.57
    POSITIVE LOGITS
     Ruhm
    0.62
     joaat
    0.60
     энциклопедия
    0.60
     Peasant
    0.59
     EdgeInsets
    0.59
    EndContext
    0.58
     henvisninger
    0.58
     adultery
    0.58
    pertory
    0.57
     interrogation
    0.56
    Activations Density 1.463%

    No Known Activations