© 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. 38-GEMMASCOPE-RES-16K
    11. 7139
    Prev
    Next
    INDEX
    Explanations

    code-related structures and data types, particularly focusing on programming and technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writerow
    -0.44
    SharedCtor
    -0.42
     outfile
    -0.41
     newArr
    -0.40
    ValueError
    -0.39
    ClientRect
    -0.39
    flashdata
    -0.38
     TypeError
    -0.36
    InteropServices
    -0.36
    fileID
    -0.35
    POSITIVE LOGITS
    {@
    0.72
     bean
    0.71
     propOrder
    0.71
     {@
    0.70
     beans
    0.66
     Bean
    0.65
     Java
    0.64
     guava
    0.63
    bean
    0.62
     JAXB
    0.61
    Activations Density 1.012%

    No Known Activations