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-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 14296
    Prev
    Next
    INDEX
    Explanations

    references to different layers in a structure or material

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    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
    -0.82
     MHD
    -0.81
    hlí
    -0.81
    DotNetBar
    -0.80
    )_/¯
    -0.78
    /**
    -0.77
    MemoryWarning
    -0.76
     Constitucional
    -0.76
    xmlhttp
    -0.75
    Dixie
    -0.75
    POSITIVE LOGITS
     Layer
    1.77
     Layers
    1.75
     layers
    1.73
     layer
    1.71
     LAYER
    1.68
    Layers
    1.65
    Layer
    1.61
    layer
    1.60
    layers
    1.53
    LAYER
    1.44
    Activations Density 0.083%

    No Known Activations