© 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. 31-GEMMASCOPE-RES-16K
    11. 681
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to inventory and order management

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

    words related to inventory, stock availability, and product fulfillment.

    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
     awakeFromNib
    -0.41
    DebuggerStep
    -0.40
    relativeTime
    -0.40
    muerzo
    -0.37
     colazione
    -0.35
    ніципа
    -0.35
    alyptus
    -0.33
     proceeded
    -0.33
    ngrx
    -0.31
     Proceeding
    -0.31
    POSITIVE LOGITS
     inventory
    1.86
     stock
    1.71
     Inventory
    1.54
    inventory
    1.52
     inventories
    1.48
    stock
    1.45
    Inventory
    1.41
     stocks
    1.41
    Stock
    1.38
     Stock
    1.37
    Activations Density 0.154%

    No Known Activations