© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2618
    Prev
    Next
    INDEX
    Explanations

    references to belts, particularly their design and functionality

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

    the word "belt" in various contexts (conveyor belts, tire belts, seat belts, and figurative uses).

    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
     kasarigan
    -0.57
     EconPapers
    -0.54
     NSCoder
    -0.54
    RenderAtEndOf
    -0.54
    AddTagHelper
    -0.53
    Espèce
    -0.48
    Dichloropropene
    -0.47
    InstrumentedTest
    -0.46
    XmlAccessorType
    -0.46
     متعلقه
    -0.46
    POSITIVE LOGITS
     belt
    2.23
     Belt
    1.95
     belts
    1.88
    Belt
    1.81
    belt
    1.77
     Belts
    1.52
    belts
    1.41
     cinturón
    1.34
    ベルト
    1.34
     ceinture
    1.29
    Activations Density 0.226%

    No Known Activations