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. 24-GEMMASCOPE-RES-16K
    6. 2392
    Prev
    Next
    INDEX
    Explanations

    references to social inequality and class dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    wealth or affluence

    np_acts-logits-general · gemini-2.0-flash

    wealth and financial security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.69
    出版年
    -0.62
    __':
    -0.55
    cinogenicity
    -0.54
     paixão
    -0.53
     IBOutlet
    -0.52
    organisme
    -0.52
    /*++
    -0.50
    dymyr
    -0.49
    nsic
    -0.48
    POSITIVE LOGITS
     wealthy
    1.17
     affluent
    1.16
     rich
    1.15
     wealth
    1.13
     prosperous
    1.08
    wealth
    1.05
     upper
    0.99
     middle
    0.98
     Wealth
    0.97
     riches
    0.96
    Activations Density 0.382%

    No Known Activations