© 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. 2778
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics in various contexts

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

    structural separators and section breaks in documents (such as blank lines, asterisks, and category headers that organize content into distinct sections).

    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
    ThroughAttribute
    -0.73
     EconPapers
    -0.69
     المعيارى
    -0.68
    点此举报
    -0.67
     dAtA
    -0.64
     utafitiHapana
    -0.61
    oredCriteria
    -0.60
    StoreMessageInfo
    -0.60
     surla
    -0.59
     BoxFit
    -0.59
    POSITIVE LOGITS
      
    0.78
       
    0.65
        
    0.40
     Khusus
    0.36
     Kebijakan
    0.35
          
    0.35
     inmediata
    0.35
     Pembangunan
    0.32
    <h2>
    0.32
    Więcej
    0.31
    Activations Density 0.128%

    No Known Activations