© 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 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. 100101
    Prev
    Next
    INDEX
    Explanations

    phrases that denote parts or sections within a context

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

    part of

    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
    :✨
    -0.36
    ApiOperation
    -0.34
    Попис
    -0.31
    anthes
    -0.31
    Diweddarwch
    -0.31
    CardHeader
    -0.31
    issements
    -0.31
    AutoScale
    -0.30
    ItemBackground
    -0.30
     chaqueta
    -0.30
    POSITIVE LOGITS
     part
    1.04
     Teil
    0.91
    part
    0.90
     parte
    0.84
     Bestandteil
    0.84
     часть
    0.83
    的一部分
    0.83
     частью
    0.82
     onderdeel
    0.81
    Part
    0.79
    Activations Density 0.048%

    No Known Activations