© 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. 44401
    Prev
    Next
    INDEX
    Explanations

    references to software components or packages typically identified as "bundles."

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

    software bundles and data containers

    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
     quadros
    -0.32
    Читати
    -0.32
     tick
    -0.28
    なこと
    -0.28
    原来的
    -0.27
     viol
    -0.27
     Saj
    -0.27
     mengakibatkan
    -0.26
     achieved
    -0.26
    由於
    -0.26
    POSITIVE LOGITS
    Bundle
    3.22
     Bundle
    2.53
    bundle
    2.22
     bundle
    2.16
     bundles
    1.84
    Bundles
    1.73
    bundles
    1.67
     Bund
    1.62
    UNDLE
    1.54
    Bund
    1.52
    Activations Density 0.000%

    No Known Activations