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. 7123
    Prev
    Next
    INDEX
    Explanations

    words related to history, anthropology, the human condition, the occult and natural phenomena

    oai_token-act-pair · gemini-2.0-flash

    psychology and human interactions

    np_max-act · 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
    ]--;
    -0.96
     resourceCulture
    -0.85
    .}~\
    -0.82
    :✨
    -0.81
    peluche
    -0.81
     continuant
    -0.80
    $.
    
    -0.80
    "])
    
    -0.79
    ?
    
    -0.78
    "],
    
    -0.78
    POSITIVE LOGITS
    <bos>
    1.93
    ↵↵
    0.79
    1
    0.75
    S
    0.73
    The
    0.71
    '
    0.70
    A
    0.68
    -
    0.67
    a
    0.66
    I
    0.64
    Activations Density 4.237%

    No Known Activations