© 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. 8136
    Prev
    Next
    INDEX
    Explanations

    references to folder and workspace-related terms within the context of a coding or API documentation

    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
    AutoScaleMode
    -0.62
    IntoConstraints
    -0.49
     nanny
    -0.47
     STATEMENTS
    -0.46
     HANDS
    -0.46
    EnableWeb
    -0.46
    gulier
    -0.46
    метров
    -0.44
    Ход
    -0.44
    ))/(
    -0.44
    POSITIVE LOGITS
    apimachinery
    0.66
    الحياه
    0.62
     Roskov
    0.61
     AssemblyTitle
    0.60
    AddTagHelper
    0.57
     Majefty
    0.57
    Identyfik
    0.57
     Perfon
    0.57
    حوالہ
    0.57
    المراجع
    0.57
    Activations Density 0.428%

    No Known Activations