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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7713
    Prev
    Next
    INDEX
    Explanations

    the word "pressure" and other words related to conflict or difficulty.

    oai_token-act-pair · gemini-2.0-flash

    pressure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     pressure
    -2.81
     Pressure
    -2.52
    pressure
    -2.50
    Pressure
    -2.48
     PRESSURE
    -2.31
     pressures
    -2.03
     presión
    -1.86
     pressão
    -1.64
     pression
    -1.63
     pressured
    -1.55
    POSITIVE LOGITS
    tvguidetime
    0.59
    HasForeignKey
    0.56
    ::_('
    0.50
     beads
    0.50
     Daarom
    0.49
    tizens
    0.48
     MainAxisSize
    0.48
    ကိုးကား
    0.48
    ftagPool
    0.48
    bead
    0.47
    Activations Density 6.798%

    No Known Activations