© 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. 4999
    Prev
    Next
    INDEX
    Explanations

    terms related to VPN and online privacy services

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

    This neuron appears to detect non-English text and foreign language content, particularly activating strongly on non-Latin characters, diacritical marks, and multi-byte character sequences from various languages including Vietnamese, Croatian, French, and others.

    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
     Infór
    -0.66
     leaſt
    -0.65
     raiſ
    -0.64
     feroit
    -0.63
     pleaſure
    -0.62
    WithIOException
    -0.59
     hırka
    -0.58
     pouvoit
    -0.58
     ainfi
    -0.56
     themſelves
    -0.56
    POSITIVE LOGITS
    .*")]
    0.51
     tra
    0.48
    numerusform
    0.47
     Pingback
    0.47
     gu
    0.46
     sk
    0.45
     Buren
    0.43
     bil
    0.43
    ondissement
    0.43
     Lenz
    0.43
    Activations Density 0.136%

    No Known Activations