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. 77095
    Prev
    Next
    INDEX
    Explanations

    instances of function declarations and control structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     pinulongan
    -1.05
    UrlResolution
    -1.01
    EndContext
    -0.98
    uxxxx
    -0.91
     estekak
    -0.87
     ویکی‌پدی
    -0.87
    AccessorTable
    -0.86
    msgTypes
    -0.78
    protoimpl
    -0.78
     <>",
    -0.77
    POSITIVE LOGITS
    The
    0.39
    Code
    0.37
    Parameter
    0.37
    PARAMETER
    0.31
     chodzi
    0.31
     
    0.31
    0.31
    Prefix
    0.30
     the
    0.30
    Definition
    0.30
    Activations Density 0.006%

    No Known Activations