© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 15014
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structures, particularly those involving input/output operations, data handling, and custom function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mesmas
    -0.55
    <bos>
    -0.52
     brancas
    -0.50
     
    -0.45
    épisode
    -0.44
     evrops
    -0.42
     abstrato
    -0.42
     institución
    -0.42
     vermelhas
    -0.42
     vermelha
    -0.41
    POSITIVE LOGITS
    SharedCtor
    0.85
     propOrder
    0.68
     ligiloj
    0.68
    oredCriteria
    0.67
    !(:
    0.67
    =`
    0.67
    ‗
    0.67
    ՚
    0.66
     zwiſchen
    0.66
     resourceCulture
    0.65
    Activations Density 3.187%

    No Known Activations