© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4873
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to the creation of objects and instances in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cumplimiento
    -0.45
     RoutedEventArgs
    -0.44
     informaciones
    -0.44
     gedrag
    -0.44
     MessageBoxIcon
    -0.42
     místa
    -0.42
     vectorielle
    -0.42
    dataIndex
    -0.42
    puerta
    -0.42
     observado
    -0.41
    POSITIVE LOGITS
     creation
    0.93
    creation
    0.86
     created
    0.84
     Creation
    0.81
    Creation
    0.79
    created
    0.76
     Create
    0.74
    创建
    0.73
     createNew
    0.72
     Creating
    0.69
    Activations Density 0.476%

    No Known Activations