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. 27-GEMMASCOPE-RES-16K
    6. 9781
    Prev
    Next
    INDEX
    Explanations

    economic indicators related to inflation and financial trends

    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
     supervivencia
    -0.38
     sobrevivir
    -0.35
     thin
    -0.35
     thinner
    -0.34
    WillAppear
    -0.34
    τε
    -0.32
     funkcji
    -0.32
     copiar
    -0.31
    gut
    -0.31
     pouvant
    -0.31
    POSITIVE LOGITS
     inflation
    0.81
     Inflation
    0.79
    Inflation
    0.77
    inflation
    0.73
    HasAnnotation
    0.68
     inflación
    0.68
     EconPapers
    0.64
     infla
    0.63
     InputDecoration
    0.61
    AnchorStyles
    0.60
    Activations Density 0.141%

    No Known Activations