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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7982
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers and values, possibly related to data structures or programming contexts

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

    numeric hexadecimal values and memory addresses.

    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
    */].
    -0.63
    談社
    -0.60
    enderror
    -0.59
     للمعارف
    -0.59
    sizeCache
    -0.58
    msgTypes
    -0.57
     ModelExpression
    -0.57
    koin
    -0.57
    ksom
    -0.57
    碕
    -0.56
    POSITIVE LOGITS
    7
    0.96
    ۷
    0.48
     zeven
    0.48
     sieben
    0.48
     siete
    0.48
    appcompat
    0.48
     Seven
    0.46
     seven
    0.45
     tujuh
    0.44
    ７
    0.44
    Activations Density 0.877%

    No Known Activations