© 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. 127361
    Prev
    Next
    INDEX
    Explanations

    words related to indicating origin or source

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

    tokens following "from"

    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
     enfans
    -0.75
     pleaſure
    -0.68
     appName
    -0.67
     perſon
    -0.65
     faſt
    -0.65
     accountId
    -0.64
     eventName
    -0.64
    ſelf
    -0.64
    JvmStatic
    -0.60
     ſtand
    -0.59
    POSITIVE LOGITS
     из
    1.33
     Из
    1.05
    Из
    1.05
    из
    0.94
     ИЗ
    0.73
     із
    0.70
     iz
    0.70
     iš
    0.66
    จาก
    0.65
     từ
    0.62
    Activations Density 0.001%

    No Known Activations