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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6890
    Prev
    Next
    INDEX
    Explanations

    words related to consideration or expectation

    oai_token-act-pair · gemini-2.0-flash

    expectations and preparation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    CopyWith
    -0.49
    ViewFeatures
    -0.48
    EDEFAULT
    -0.47
     GenerationType
    -0.46
    ISPR
    -0.46
    BeginContext
    -0.46
    lète
    -0.46
    逅
    -0.46
    melons
    -0.45
    NSU
    -0.44
    POSITIVE LOGITS
     initComponents
    0.67
    MigrationBuilder
    0.59
     endblock
    0.58
    ("")]
    
    0.56
    UserScript
    0.52
    USTER
    0.52
    :"-"`
    0.52
    reportWebVitals
    0.50
    ::::::::
    0.50
    новништво
    0.50
    Activations Density 0.412%

    No Known Activations