© 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. 9-GEMMASCOPE-RES-131K
    11. 96124
    Prev
    Next
    INDEX
    Explanations

    references to quantities and their significance in various contexts

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

    large amounts or size

    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
     BoxFit
    -0.48
    较为
    -0.47
     tolerably
    -0.47
    \{\\
    -0.46
     EconPapers
    -0.45
    ValueGeneration
    -0.45
     Occasional
    -0.43
     satisfactory
    -0.42
     satisfactorily
    -0.42
    jsxFileName
    -0.42
    POSITIVE LOGITS
    Huge
    1.17
     huge
    1.16
    huge
    1.13
     Huge
    1.05
     enormous
    1.02
     énorme
    1.01
     enormes
    1.00
     HUGE
    0.97
     огром
    0.96
    ormous
    0.96
    Activations Density 0.028%

    No Known Activations