Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 12854
    Prev
    Next
    INDEX
    Explanations

    references to inventory and stock availability

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

    stock and availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    verwijspagina
    -0.64
    appé
    -0.56
    WriteTagHelper
    -0.55
    IndentedString
    -0.55
    enterOuterAlt
    -0.53
    Попис
    -0.50
    onViewCreated
    -0.50
    
    -0.49
     незавершена
    -0.49
    HasForeignKey
    -0.48
    POSITIVE LOGITS
     stock
    1.09
     availability
    1.09
     available
    1.08
     Available
    0.92
    Available
    0.90
     disponible
    0.89
     Availability
    0.88
     Stock
    0.88
    available
    0.88
     availa
    0.86
    Activations Density 0.005%

    No Known Activations