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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 58774
    Prev
    Next
    INDEX
    Explanations

    references to system calls related to file operations in a programming context

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

    sys function names and system calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    multicolumn
    -0.58
     Bookmark
    -0.56
     CreateTagHelper
    -0.55
    addElement
    -0.52
    gerald
    -0.52
    جمعیت
    -0.51
    crumb
    -0.48
    orant
    -0.48
    afd
    -0.47
    ️
    -0.46
    POSITIVE LOGITS
     sys
    1.23
     Sys
    1.17
    sys
    1.10
    Sys
    1.08
     SYS
    0.96
    SYS
    0.88
    SysUser
    0.84
    ys
    0.72
     Szy
    0.65
    getSystem
    0.65
    Activations Density 0.016%

    No Known Activations