© 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. 13529
    Prev
    Next
    INDEX
    Explanations

    concepts related to interpersonal relationships and connections

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

    phrases describing comparative relationships or interactions between two distinct entities or groups.

    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
    Affiliations
    -0.29
    Every
    -0.25
    жает
    -0.23
    toarele
    -0.22
     olvid
    -0.22
    ợp
    -0.22
    iasaan
    -0.21
     Every
    -0.21
     klart
    -0.21
    Out
    -0.21
    POSITIVE LOGITS
     nhau
    1.92
     eachother
    1.92
     друг
    1.91
     elkaar
    1.80
     varandra
    1.80
    彼此
    1.66
     einander
    1.56
    กัน
    1.51
     birbir
    1.46
    お互
    1.44
    Activations Density 0.418%

    No Known Activations