Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 13686
    Prev
    Next
    INDEX
    Explanations

    references to database connection strings and local package management in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -1.03
    RegressionTest
    -1.02
     hObject
    -0.98
    setVerticalGroup
    -0.98
     Roskov
    -0.94
    UnusedPrivate
    -0.93
    +:+
    -0.90
    Personendaten
    -0.89
     AssemblyCulture
    -0.86
    WriteTagHelper
    -0.86
    POSITIVE LOGITS
     SqlConnection
    1.23
     WaitForSeconds
    1.05
    AtIndexPath
    0.93
     tkinter
    0.84
    packages
    0.77
    ModelSerializer
    0.73
     MemoryStream
    0.73
    ↗
    0.66
    MemoryStream
    0.65
     mxArray
    0.65
    Activations Density 0.005%

    No Known Activations