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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4966
    Prev
    Next
    INDEX
    Explanations

    terms related to the transfer and distribution of resources or rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viewDidLoad
    -0.71
    ArgsConstructor
    -0.59
    ENDENT
    -0.58
    Carriera
    -0.54
     recensement
    -0.53
    ionView
    -0.53
     Phone
    -0.51
    wini
    -0.50
    ActiveRecord
    -0.50
    anchor
    -0.49
    POSITIVE LOGITS
     distributes
    0.82
     distribute
    0.79
     distributing
    0.74
     handing
    0.74
     kepada
    0.73
    distribute
    0.72
     delivered
    0.72
     handouts
    0.71
     delivery
    0.71
     truyền
    0.71
    Activations Density 0.481%

    No Known Activations