© 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. 10-GEMMASCOPE-RES-16K
    11. 6416
    Prev
    Next
    INDEX
    Explanations

    terms related to manufacturing processes and product specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.69
    exitRule
    -0.65
     كومونز
    -0.61
    DeleteBehavior
    -0.60
    
    -0.58
     nakalista
    -0.57
     utafitiHapana
    -0.56
     CURIAM
    -0.56
     disambiguazione
    -0.55
    verwijspagina
    -0.55
    POSITIVE LOGITS
     manufacture
    0.57
    manufact
    0.57
     manufactured
    0.56
     manufacturers
    0.54
     manufacturer
    0.52
     Manufacturers
    0.52
     MANUFACT
    0.49
    manufactured
    0.48
    :✨
    0.47
     manufactures
    0.47
    Activations Density 3.343%

    No Known Activations