© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7563
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTLD
    -0.42
     kasarigan
    -0.42
    RegressionTest
    -0.41
    Workbook
    -0.35
    Personendaten
    -0.34
    cyklo
    -0.34
    avajillas
    -0.34
    脚注の使い方
    -0.33
     Ellison
    -0.33
     समीक्षक
    -0.33
    POSITIVE LOGITS
     react
    0.97
     React
    0.96
     Angular
    0.92
     angular
    0.85
     Vue
    0.84
     vue
    0.81
    nestjs
    0.77
    react
    0.76
     Node
    0.75
    React
    0.75
    Activations Density 0.936%

    No Known Activations