© 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. 28-GEMMASCOPE-RES-16K
    11. 12005
    Prev
    Next
    INDEX
    Explanations

    keywords related to wax, particularly in various contexts such as food or materials

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

    Wax, paraffin, melting

    np_acts-logits-general · gemini-2.0-flash

    wax, paraffin, candles, melting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     kasarigan
    -0.53
    hysema
    -0.44
    
    -0.43
     panneau
    -0.42
     Normdatei
    -0.42
     linkovi
    -0.41
    pneum
    -0.39
     Autorisations
    -0.39
     inflection
    -0.39
     ventilator
    -0.39
    POSITIVE LOGITS
     wax
    1.28
     Wax
    1.08
    wax
    1.03
    Wax
    0.98
     melting
    0.95
     melted
    0.94
     melts
    0.93
     melt
    0.89
     candle
    0.88
     candles
    0.82
    Activations Density 0.302%

    No Known Activations