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. 8-GEMMASCOPE-RES-16K
    6. 4671
    Prev
    Next
    INDEX
    Explanations

    terms related to financial regulations and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.88
     CreateTagHelper
    -0.81
    AnchorStyles
    -0.73
     CCPA
    -0.70
    ValueStyle
    -0.69
    complexContent
    -0.68
    VersionUID
    -0.64
     BoxFit
    -0.63
    setViewportView
    -0.61
    bootstrapcdn
    -0.61
    POSITIVE LOGITS
    TextWatcher
    0.55
    <()>
    0.55
     network
    0.55
     banking
    0.54
     carrier
    0.52
     trans
    0.49
     remittances
    0.47
     relay
    0.47
    yuan
    0.45
    PMailer
    0.45
    Activations Density 0.196%

    No Known Activations