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. 14089
    Prev
    Next
    INDEX
    Explanations

    terms related to employment and tax liabilities

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

    First word in legal or business contexts

    np_acts-logits-general · gemini-2.0-flash

    legal reliance and election

    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
    yargs
    -0.64
     réflé
    -0.57
     <<<<<<<<<<<<<<
    -0.57
     erz
    -0.54
    τζ
    -0.53
    toria
    -0.52
    تقاوى
    -0.52
    vist
    -0.52
    ImageContext
    -0.51
    complexContent
    -0.51
    POSITIVE LOGITS
    URLException
    0.65
     thereafter
    0.61
    Carriera
    0.60
     timely
    0.60
     Seeder
    0.59
     thereto
    0.58
    GEBURTSDATUM
    0.58
     furnished
    0.57
     elect
    0.54
     thereupon
    0.53
    Activations Density 1.424%

    No Known Activations