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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7788
    Prev
    Next
    INDEX
    Explanations

    references to India and its regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.75
    SourceChecksum
    -0.72
     Coruña
    -0.68
     Enugu
    -0.67
     BAST
    -0.66
     RequestMethod
    -0.66
     Brawl
    -0.65
     Memes
    -0.63
     Aleks
    -0.63
     Lent
    -0.63
    POSITIVE LOGITS
     India
    1.62
     Indian
    1.44
     Indians
    1.41
    Indians
    1.39
    India
    1.39
     india
    1.32
    indian
    1.31
    Indian
    1.30
     INDIA
    1.27
    INDIAN
    1.26
    Activations Density 0.063%

    No Known Activations