© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 81601
    Prev
    Next
    INDEX
    Explanations

    references to PSA (prostate-specific antigen) and related prostate cancer terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    PSA or Peugeot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Distribuzione
    -0.44
     sinks
    -0.39
     يتيمه
    -0.38
     وتسجيلات
    -0.38
    हन
    -0.37
    allowNull
    -0.36
    着他
    -0.35
    ัพท์
    -0.35
     různ
    -0.35
     farms
    -0.35
    POSITIVE LOGITS
     PSA
    2.67
    PSA
    2.30
     psa
    1.65
    psa
    1.52
     PS
    0.91
     Peugeot
    0.81
    PS
    0.75
    Peugeot
    0.74
    pso
    0.71
     PSO
    0.71
    Activations Density 0.005%

    No Known Activations