© 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
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 12260
    Prev
    Next
    INDEX
    Explanations

    deterministic variables and mathematical notations related to matrices and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.46
     EconPapers
    -0.46
    extAlignment
    -0.44
    richTextPanel
    -0.43
     وتسجيلات
    -0.42
     oprot
    -0.40
     Baillargeon
    -0.39
     pouvoit
    -0.38
    astéroïdes
    -0.38
    expandindo
    -0.38
    POSITIVE LOGITS
     indicates
    1.73
     denotes
    1.70
     indicate
    1.65
     indicating
    1.61
     denote
    1.59
     denoting
    1.55
     signifies
    1.46
     signify
    1.45
     designates
    1.37
    indicates
    1.37
    Activations Density 1.375%

    No Known Activations