© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9270
    Prev
    Next
    INDEX
    Explanations

    clauses that contain the word "which" indicating conditions or relationships in the context of reasoning or legal discussions

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

    "which" followed by a noun or pronoun

    np_acts-logits-general · gemini-2.0-flash

    for which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     likeness
    -0.56
    теризу
    -0.54
     acquaintance
    -0.54
    stateProvider
    -0.54
     hearers
    -0.52
    AlterField
    -0.51
     Jefus
    -0.50
    copg
    -0.49
    //
    -0.49
     hyperplasia
    -0.48
    POSITIVE LOGITS
     Dafür
    0.73
     purposes
    0.71
    LookAnd
    0.68
    complexContent
    0.64
    SuspendLayout
    0.61
     désolés
    0.61
     تضيفلها
    0.60
     Paglinawan
    0.59
     purpose
    0.58
     Purposes
    0.58
    Activations Density 0.179%

    No Known Activations