© 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. 14-GEMMASCOPE-RES-16K
    11. 8670
    Prev
    Next
    INDEX
    Explanations

    the character 'x' in various contexts, likely signifying some form of data encoding or representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gleich
    -0.33
     pł
    -0.30
     spesa
    -0.30
     aéreo
    -0.30
     gelijk
    -0.28
     guía
    -0.28
     הש
    -0.27
     titulares
    -0.27
    eadilan
    -0.27
     remaining
    -0.26
    POSITIVE LOGITS
     kasarigan
    0.96
    ViewFeatures
    0.94
    الدراسه
    0.85
    RegressionTest
    0.85
    
    0.83
    TagMode
    0.81
    出版年
    0.80
    ValueStyle
    0.79
    EndProject
    0.79
     незавершена
    0.78
    Activations Density 0.048%

    No Known Activations