© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9724
    Prev
    Next
    INDEX
    Explanations

    specific sizes and dimensions related to products or items

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

    watches

    np_acts-logits-general · gemini-2.0-flash

    watch, medal, smartwatch

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    rungsseite
    -0.59
    Viitteet
    -0.48
     desglose
    -0.47
    Rptr
    -0.46
     שוליים
    -0.46
    хьтан
    -0.45
    ereich
    -0.44
    requis
    -0.43
    onames
    -0.43
    窟
    -0.43
    POSITIVE LOGITS
     medal
    0.58
     Medal
    0.53
     medals
    0.47
     smartwatch
    0.47
     watch
    0.46
    medal
    0.46
    Medal
    0.43
     Medals
    0.42
    writeField
    0.41
    watch
    0.39
    Activations Density 0.165%

    No Known Activations