© 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. 31-GEMMASCOPE-RES-16K
    11. 2657
    Prev
    Next
    INDEX
    Explanations

    technical terms and constructs related to JSON and XML data formatting and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    JSON serialization and deserialization code patterns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.46
     Italijanski
    -0.45
    Rujuakan
    -0.45
     linkovi
    -0.43
     resourceCulture
    -0.43
     ivelany
    -0.43
     pério
    -0.40
     pocz
    -0.40
    couvrez
    -0.40
     שוליים
    -0.40
    POSITIVE LOGITS
     conversions
    0.71
     converting
    0.69
     conversion
    0.69
     converter
    0.68
     converters
    0.66
     Conversion
    0.63
    Conversion
    0.62
     converts
    0.61
    conversion
    0.60
     AutoMapper
    0.59
    Activations Density 0.634%

    No Known Activations