© 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. 15-GEMMASCOPE-RES-16K
    6. 1690
    Prev
    Next
    INDEX
    Explanations

    concepts related to peace and harmony

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ToObject
    -0.50
     Foire
    -0.46
     wireType
    -0.44
     Company
    -0.44
     NSCoder
    -0.43
    xdr
    -0.41
     Heuer
    -0.41
     voiture
    -0.41
     Mattel
    -0.41
     CEO
    -0.40
    POSITIVE LOGITS
     peace
    1.39
     PEACE
    1.38
    peace
    1.30
     Peace
    1.22
    Peace
    1.21
    PEACE
    1.20
     peaceful
    1.13
    Peaceful
    1.10
     Peaceful
    1.09
     peacefully
    1.05
    Activations Density 0.217%

    No Known Activations