Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7065
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to Indian culture and cuisine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getDoctrine
    -0.50
     linguri
    -0.44
    lepaskan
    -0.40
     picioare
    -0.38
    enderror
    -0.37
     maș
    -0.37
    warnai
    -0.35
     Privacidad
    -0.32
    Còn
    -0.32
     locul
    -0.32
    POSITIVE LOGITS
     India
    2.06
     Indian
    1.99
    India
    1.91
    Indian
    1.86
     INDIA
    1.77
    印度
    1.71
     indian
    1.70
     INDIAN
    1.70
     india
    1.67
     Indians
    1.64
    Activations Density 0.544%

    No Known Activations