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. 7-GEMMASCOPE-RES-16K
    6. 8730
    Prev
    Next
    INDEX
    Explanations

    programming and coding-related syntax elements, particularly those used in defining functions and code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alnız
    -0.67
    ]='\
    -0.66
    ngdoc
    -0.61
     المعيارى
    -0.61
    sieurs
    -0.60
     testGet
    -0.59
     Giud
    -0.58
    lammatory
    -0.56
    weder
    -0.56
    AddHtmlAttribute
    -0.56
    POSITIVE LOGITS
    مصادر
    0.64
    Says
    0.58
    
    0.53
    -------
    0.50
    xyz
    0.46
     said
    0.46
     dijo
    0.45
     armed
    0.45
     StatefulWidget
    0.45
    nergie
    0.43
    Activations Density 0.247%

    No Known Activations