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. 18-GEMMASCOPE-RES-16K
    6. 3740
    Prev
    Next
    INDEX
    Explanations

    terms related to legal contracts and proceedings

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

    Government contracting/procurement

    np_acts-logits-general · gemini-2.0-flash

    procurement, purchasing, contracting, buying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.61
    AddField
    -0.48
     surla
    -0.46
     disambiguazione
    -0.46
    WireFormatLite
    -0.45
     ContentValues
    -0.44
    AsUp
    -0.43
    greenrobot
    -0.43
    estens
    -0.43
    COUVER
    -0.43
    POSITIVE LOGITS
     procurement
    1.49
     Procurement
    1.38
     purchasing
    1.31
     Purchasing
    1.25
    Procurement
    1.23
     contracts
    1.11
     procuring
    1.08
    purch
    1.08
    Purchasing
    1.08
     buying
    1.06
    Activations Density 0.187%

    No Known Activations