© 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
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 11425
    Prev
    Next
    INDEX
    Explanations

    structures that resemble or represent data entries or database-like formats, specifically looking for key-value pairs, regions, and codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.55
     getInstance
    -0.49
    enumi
    -0.49
     addObject
    -0.46
     whiteColor
    -0.44
     itemList
    -0.44
    PerformLayout
    -0.43
     setContent
    -0.43
     getResult
    -0.43
     getColumn
    -0.43
    POSITIVE LOGITS
     subtype
    0.50
     rainha
    0.47
    othelioma
    0.46
     hidden
    0.45
     type
    0.45
     compless
    0.45
    verwijspagina
    0.44
     name
    0.44
     Roskov
    0.43
    WebServlet
    0.42
    Activations Density 0.373%

    No Known Activations