Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105455
    Prev
    Next
    INDEX
    Explanations

    contexts related to the concept of design, including the act of creating or planning something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.63
     pinulongan
    -0.58
    Abraço
    -0.51
     geloof
    -0.50
     segurando
    -0.49
    ########.
    -0.47
    endpush
    -0.47
    Архівовано
    -0.47
    gelopen
    -0.46
     esternos
    -0.45
    POSITIVE LOGITS
     designing
    1.02
     designed
    1.02
     design
    1.00
    designed
    0.94
     DESIGN
    0.93
     Designed
    0.92
    Designing
    0.90
     Designing
    0.87
    Designed
    0.87
    設計
    0.84
    Activations Density 0.032%

    No Known Activations