© 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. 31-GEMMASCOPE-RES-16K
    11. 14540
    Prev
    Next
    INDEX
    Explanations

    instances of the word "made" in various forms and contexts

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

    the word "made" followed by descriptive context about what something is manufactured for or from.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aktery
    -0.52
    potranspiration
    -0.48
     surla
    -0.48
     indisponible
    -0.47
     <>",
    -0.46
     pleaſure
    -0.45
     themſelves
    -0.45
    endregion
    -0.45
    はじめに
    -0.44
    ruik
    -0.43
    POSITIVE LOGITS
     Made
    0.50
    Made
    0.49
    LookAnd
    0.42
    MADE
    0.42
    elemField
    0.41
    prepareStatement
    0.40
     Vau
    0.40
     MADE
    0.39
    TestingModule
    0.38
    withIdentifier
    0.37
    Activations Density 0.289%

    No Known Activations