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

    Neuronpedia

    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. 28-GEMMASCOPE-RES-16K
    11. 5077
    Prev
    Next
    INDEX
    Explanations

    requests and petitions for various forms of assistance or legal actions

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

    Requests or petitions

    np_acts-logits-general · gemini-2.0-flash

    requesting formal permission or action

    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
    InputBorder
    -0.50
    TypeDef
    -0.43
     setEmail
    -0.41
    ్రామ
    -0.41
     tegens
    -0.39
    InjectMocks
    -0.38
     handleMessage
    -0.38
    Thể
    -0.36
     onSuccess
    -0.36
    initializeApp
    -0.36
    POSITIVE LOGITS
     help
    0.74
     assistance
    0.71
     hjälp
    0.67
     bantuan
    0.65
     помощи
    0.64
    help
    0.61
     permission
    0.61
     Hilfe
    0.60
     ayuda
    0.59
    assistance
    0.59
    Activations Density 0.452%

    No Known Activations