© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 5846
    Prev
    Next
    INDEX
    Explanations

    historical references to political entities and territorial disputes

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

    historical and political narrative about European territorial disputes, succession laws, and dynastic conflicts.

    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
     Cæsar
    -0.90
    ſelves
    -0.87
     Majefty
    -0.83
     Monfieur
    -0.81
     Shakspeare
    -0.75
     voodoo
    -0.74
    ſelf
    -0.73
     myſelf
    -0.73
     itſelf
    -0.72
     Efq
    -0.71
    POSITIVE LOGITS
     hospod
    0.37
     refroidissement
    0.36
     záz
    0.36
     hidráulica
    0.36
     embreagem
    0.36
     médié
    0.35
     tulisan
    0.34
     hånd
    0.34
     tjen
    0.33
     wijn
    0.33
    Activations Density 1.432%

    No Known Activations