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. 2020
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to database connections and operations

    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
    hasMoreElements
    -0.64
     protoimpl
    -0.62
     SwiftUI
    -0.61
    mergeFrom
    -0.55
    richTextPanel
    -0.54
     lipat
    -0.54
    umenten
    -0.54
    ẨM
    -0.53
    NOPQRST
    -0.53
    AutoScale
    -0.52
    POSITIVE LOGITS
    DriverManager
    0.79
     SqlConnection
    0.77
    SqlClient
    0.73
     connection
    0.71
     Connection
    0.70
     дописавши
    0.70
    Connection
    0.69
     psycopg
    0.68
     विश्वसनीयता
    0.66
    oa̍t
    0.62
    Activations Density 0.222%

    No Known Activations