© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 942
    Prev
    Next
    INDEX
    Explanations

    references to financial challenges and the middle class's economic struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يديا
    -0.32
     esternos
    -0.31
    違和感
    -0.30
    ocere
    -0.30
     пробу
    -0.29
    glise
    -0.28
    Nazionale
    -0.28
    融合
    -0.27
     contaminant
    -0.27
    Complex
    -0.27
    POSITIVE LOGITS
     financially
    1.78
     financial
    1.75
     finances
    1.69
     budgeting
    1.60
    financial
    1.59
     money
    1.56
    financi
    1.55
     budget
    1.49
     budgets
    1.49
     financi
    1.44
    Activations Density 0.904%

    No Known Activations