© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 49692
    Prev
    Next
    INDEX
    Explanations

    commands and terms related to sorting and ordering

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

    sort and order

    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
     screenWidth
    -0.59
     Entra
    -0.54
    screenWidth
    -0.53
    LocalizedString
    -0.52
     Helios
    -0.52
    ExecutionContext
    -0.50
    marginHorizontal
    -0.50
     newUser
    -0.50
     препратки
    -0.50
     Mila
    -0.49
    POSITIVE LOGITS
    sort
    1.15
     Sort
    1.11
    Sort
    1.10
     sort
    1.02
     SORT
    1.00
    SORT
    0.98
     sorting
    0.88
    sorting
    0.86
     Sorting
    0.85
    Sorting
    0.78
    Activations Density 0.008%

    No Known Activations