© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 8531
    Prev
    Next
    INDEX
    Explanations

    terms related to China and its economic expansion on a global scale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Composable
    -0.50
     valmis
    -0.49
     forfeiture
    -0.47
     Warszawie
    -0.46
     sauvages
    -0.45
    componentWill
    -0.45
     Träger
    -0.44
     undergoing
    -0.44
     useRef
    -0.42
    espół
    -0.42
    POSITIVE LOGITS
     market
    1.01
     markets
    0.99
     Market
    0.90
     MARKET
    0.85
     Markets
    0.84
    Market
    0.83
     MARKETS
    0.80
    markets
    0.80
    market
    0.80
     mercados
    0.79
    Activations Density 0.195%

    No Known Activations