© 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. 3-GEMMASCOPE-RES-16K
    11. 9807
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.68
    IntoConstraints
    -0.65
     protoimpl
    -0.60
     ſta
    -0.59
     ſte
    -0.56
     myſelf
    -0.55
     leſs
    -0.54
     للمعارف
    -0.52
     ſch
    -0.52
     faſt
    -0.52
    POSITIVE LOGITS
     desarrollado
    0.45
     ruinas
    0.43
    UIControlState
    0.42
     developed
    0.40
     aislado
    0.39
     muñeca
    0.39
     diep
    0.39
     ogen
    0.38
     desarrollar
    0.38
    synthesize
    0.38
    Activations Density 0.141%

    No Known Activations