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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12620
    Prev
    Next
    INDEX
    Explanations

    specific genetic terms and identifiers related to diseases

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

    KD, kd, Kd, KDIGO, KDDCUP99, peptide

    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
    UIC
    -0.39
    strerror
    -0.37
     Berthe
    -0.37
     transition
    -0.35
     combination
    -0.35
    liess
    -0.34
     resist
    -0.34
    ɬ
    -0.34
    agoza
    -0.34
     solas
    -0.34
    POSITIVE LOGITS
     KD
    2.31
    KD
    2.14
     kd
    1.88
    kd
    1.82
    Kd
    1.55
     CKD
    0.77
     KDE
    0.77
     Cd
    0.73
     Durant
    0.72
     knockdown
    0.72
    Activations Density 0.009%

    No Known Activations