© 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. 15771
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and mathematical functions

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

    assignment operators and mathematical operations in code.

    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
    extAlignment
    -0.46
    #
    -0.40
    躇
    -0.40
     newBuilder
    -0.39
     Astrid
    -0.39
    rode
    -0.38
    Попис
    -0.38
    riek
    -0.37
    adro
    -0.36
     Cipri
    -0.36
    POSITIVE LOGITS
     max
    1.20
     whichever
    1.19
    max
    1.07
     min
    1.00
     Max
    0.93
    Max
    0.91
     MAX
    0.90
    min
    0.90
     maximum
    0.89
     minimum
    0.88
    Activations Density 0.441%

    No Known Activations