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. 16-GEMMASCOPE-RES-16K
    6. 689
    Prev
    Next
    INDEX
    Explanations

    corporate and industrial terminology related to manufacturing and supply chains

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

    Products, components, or instruments

    np_acts-logits-general · gemini-2.0-flash

    commercial products services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.84
    sizeCache
    -0.69
    MethodManager
    -0.69
    CloseOperation
    -0.68
    prepareStatement
    -0.68
    Hochspringen
    -0.67
     ProtoMessage
    -0.67
     noDo
    -0.63
     CreateTagHelper
    -0.63
     MainAxisSize
    -0.62
    POSITIVE LOGITS
     products
    0.81
     solutions
    0.71
     premium
    0.64
     Grüßen
    0.61
     innovative
    0.60
     specialty
    0.60
     προϊόν
    0.56
     product
    0.56
     niche
    0.55
    主力
    0.54
    Activations Density 0.293%

    No Known Activations