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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7578
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of components and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a component/part of something

    np_acts-logits-general · gemini-2.0-flash

    comprising a component

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.45
     craindre
    -0.39
    #+#
    -0.39
     exercí
    -0.38
     виправивши
    -0.38
     trám
    -0.37
     défendre
    -0.37
    另一种
    -0.36
     banyo
    -0.36
     nôtre
    -0.35
    POSITIVE LOGITS
     main
    0.94
     core
    0.76
    main
    0.74
     MAIN
    0.73
     Main
    0.73
    主
    0.71
     outer
    0.71
    主体
    0.68
    本体
    0.68
     front
    0.66
    Activations Density 1.429%

    No Known Activations