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. 1580
    Prev
    Next
    INDEX
    Explanations

    references to data management and database-related terminology

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

    Items related to logs, databases, and file lists

    np_acts-logits-general · gemini-2.0-flash

    data structures and lists

    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
    complexContent
    -0.52
    IndentedString
    -0.50
    lant
    -0.48
     AssemblyTitle
    -0.48
     Wearing
    -0.48
    imak
    -0.47
    Wearing
    -0.47
     Excellency
    -0.47
     DBNull
    -0.46
    THO
    -0.46
    POSITIVE LOGITS
     lists
    0.75
    IsContent
    0.73
     يتيمه
    0.72
     list
    0.69
     itemList
    0.67
     listes
    0.65
     consisting
    0.64
    TestingModule
    0.63
     rhestr
    0.60
    VENTORY
    0.60
    Activations Density 0.633%

    No Known Activations