© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9386
    Prev
    Next
    INDEX
    Explanations

    concepts related to sustainability and ethical practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.38
    Formazione
    -0.36
     subordinate
    -0.36
     églises
    -0.34
     mémor
    -0.34
     préparation
    -0.34
     Insurance
    -0.32
     expérimentés
    -0.32
     ressemb
    -0.32
     pening
    -0.32
    POSITIVE LOGITS
     ecologically
    1.01
     eco
    0.97
     environmentally
    0.96
     Eco
    0.91
     ecological
    0.90
     recycle
    0.90
     sustainability
    0.88
    Eco
    0.87
     ecology
    0.84
    eco
    0.81
    Activations Density 0.196%

    No Known Activations