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. 17-GEMMASCOPE-RES-16K
    6. 1159
    Prev
    Next
    INDEX
    Explanations

    text related to financial transactions, legal agreements, and insurance-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.66
     tartalomajánló
    -0.64
     quelli
    -0.64
    MigrationBuilder
    -0.62
     שוליים
    -0.62
    queles
    -0.62
    larım
    -0.61
    олові
    -0.59
    larımız
    -0.59
    ImageContext
    -0.59
    POSITIVE LOGITS
    该
    0.90
     this
    0.77
    該
    0.74
     该
    0.68
     the
    0.63
    这款
    0.57
     این
    0.54
    这部
    0.53
    this
    0.52
     it
    0.52
    Activations Density 0.971%

    No Known Activations