© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 9028
    Prev
    Next
    INDEX
    Explanations

    references to wars, peace processes, and human rights awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.48
     cavalier
    -0.42
     tiện
    -0.39
    jsii
    -0.38
     inefficiency
    -0.38
    moveToNext
    -0.37
     inefficient
    -0.36
    antwortung
    -0.36
     fidèle
    -0.36
    IZONA
    -0.36
    POSITIVE LOGITS
     peace
    3.09
     Peace
    2.64
    peace
    2.61
    Peace
    2.52
     PEACE
    2.39
    PEACE
    2.22
     peaceful
    2.09
     Peaceful
    1.79
     peacefully
    1.78
    和平
    1.78
    Activations Density 0.530%

    No Known Activations