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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14627
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and deployment pipelines

    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
     computadora
    -0.40
     computador
    -0.37
    ordinateur
    -0.37
     Soriano
    -0.36
     eletrônico
    -0.36
    graphics
    -0.35
     ordinateur
    -0.34
    FormatException
    -0.33
    QMetaType
    -0.33
    prefs
    -0.32
    POSITIVE LOGITS
     deployments
    1.01
     deployment
    0.98
     onboarding
    0.95
     integrations
    0.90
     deploy
    0.90
    Personensuche
    0.89
     deployed
    0.86
     deploying
    0.85
     Deploy
    0.84
     provisioning
    0.84
    Activations Density 0.776%

    No Known Activations