Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 6188
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to financial crimes or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ***!
    -0.72
     Réponses
    -0.66
    Datuak
    -0.63
     оригіналу
    -0.62
     nothing
    -0.61
     <<<<<<<<<<<<<<
    -0.60
    HasAnnotation
    -0.59
    wapV
    -0.59
     EconPapers
    -0.57
    gonic
    -0.56
    POSITIVE LOGITS
    TemporalType
    0.49
     dönem
    0.48
     millions
    0.48
    ített
    0.48
     Méditerranée
    0.48
    nanoTime
    0.48
    :]:
    0.48
     consultato
    0.47
    Alleg
    0.46
     vendu
    0.46
    Activations Density 0.790%

    No Known Activations