© 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. 40-GEMMASCOPE-RES-16K
    6. 5024
    Prev
    Next
    INDEX
    Explanations

    terms related to building and creating structures and relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recién
    -0.52
    脚注の使い方
    -0.49
    Manbalar
    -0.48
    abstractmethod
    -0.47
    stdc
    -0.47
    ViewImports
    -0.46
     ब्रेकडाउन
    -0.45
    tilization
    -0.44
    WebServlet
    -0.43
     Verfügung
    -0.42
    POSITIVE LOGITS
     friendships
    0.77
     bridges
    0.75
     relationships
    0.74
     bonds
    0.74
     rapport
    0.72
     partnerships
    0.71
     networks
    0.70
     alliances
    0.70
     awareness
    0.67
     linkages
    0.67
    Activations Density 0.523%

    No Known Activations