© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15612
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with the concept of "declaration" and "decade"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Starts with "dec" or "DEC"

    np_acts-logits-general · gemini-2.0-flash

    Dec/dec/deca prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    kiss
    -0.46
    lessly
    -0.40
    sena
    -0.40
    plyr
    -0.39
    vo
    -0.39
    KISS
    -0.39
     hola
    -0.39
     Provision
    -0.39
    visiting
    -0.38
     contr
    -0.37
    POSITIVE LOGITS
     Dec
    0.97
    Dec
    0.94
     DEC
    0.91
    DEC
    0.88
     dec
    0.80
     deca
    0.76
     Decker
    0.74
     Dek
    0.70
     nahilalakip
    0.67
    dec
    0.66
    Activations Density 0.181%

    No Known Activations