© 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. 31-GEMMASCOPE-RES-131K
    11. 6568
    Prev
    Next
    INDEX
    Explanations

    terms related to "pedigree" and various contexts involving the prefix "ped."

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

    pedunculated, pedigree, pedophile, pediatric, pedals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    กรณ์
    -0.34
     curse
    -0.33
    Curse
    -0.31
    kijken
    -0.31
    точно
    -0.30
    CharStream
    -0.30
     visible
    -0.29
    눠
    -0.29
    fjspx
    -0.29
    一眼
    -0.29
    POSITIVE LOGITS
     Ped
    1.10
     ped
    1.07
    Ped
    1.02
    ped
    0.89
     PED
    0.85
     pedic
    0.82
     pedi
    0.75
     pedest
    0.73
    PED
    0.71
     pedals
    0.70
    Activations Density 0.011%

    No Known Activations