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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114628
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to function and member expressions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    AndEndTag
    -0.52
    AndroidJUnit
    -0.50
    writeField
    -0.42
    CppMethod
    -0.40
    AppMethodBeat
    -0.40
     demais
    -0.39
    inheritDoc
    -0.36
    BuildContext
    -0.36
     testCase
    -0.36
    StoryboardSegue
    -0.35
    POSITIVE LOGITS
     AssemblyCulture
    0.69
    aarrggbb
    0.53
     OFDb
    0.51
    
    0.49
    SuspendLayout
    0.49
    BaseAdapter
    0.47
     lone
    0.46
    
    0.45
     alibi
    0.43
     solitary
    0.43
    Activations Density 0.038%

    No Known Activations