© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 1427
    Prev
    Next
    INDEX
    Explanations

    concepts related to pneumatic systems and components

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

    air and pressure systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     invokingState
    -0.48
     MutableLiveData
    -0.47
    mitian
    -0.47
     inciner
    -0.47
     Nucleic
    -0.45
     incin
    -0.45
    onuc
    -0.44
     plagiarism
    -0.43
     gewor
    -0.42
    ophosph
    -0.42
    POSITIVE LOGITS
     pressure
    0.63
     pump
    0.57
     pressurized
    0.55
     pumps
    0.54
     gas
    0.54
     Pressure
    0.53
     compression
    0.53
     PRESSURE
    0.53
     filled
    0.52
    pressure
    0.51
    Activations Density 0.086%

    No Known Activations