© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5243
    Prev
    Next
    INDEX
    Explanations

    references to the arXiv preprint server

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
    SequentialGroup
    -1.32
    graphicx
    -0.88
     CreateTagHelper
    -0.88
    addCriterion
    -0.85
    Personendaten
    -0.75
    ScopeManager
    -0.75
    NameInMap
    -0.64
    amsmath
    -0.63
    amssymb
    -0.63
     resourceCulture
    -0.58
    POSITIVE LOGITS
    arXiv
    2.27
    ParallelGroup
    1.31
     USP
    1.13
    cshtml
    0.89
     arXiv
    0.88
    USP
    0.85
    Становништво
    0.71
    addGroup
    0.70
    PROTOBUF
    0.57
     insuffisamment
    0.57
    Activations Density 0.042%

    No Known Activations