© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 110828
    Prev
    Next
    INDEX
    Explanations

    Java method declarations and annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    
    -0.54
    WriteTagHelper
    -0.52
     themſelves
    -0.50
    joba
    -0.50
     استنادى
    -0.49
     diagonal
    -0.48
    UnitTesting
    -0.48
    XmlAttribute
    -0.47
     diagonals
    -0.47
    хьтан
    -0.47
    POSITIVE LOGITS
     onCreateView
    0.56
    LayoutInflater
    0.39
    createView
    0.38
     views
    0.38
     kaarangay
    0.36
    ableView
    0.35
    initView
    0.34
     Views
    0.34
    setContentView
    0.34
     VIEWS
    0.34
    Activations Density 0.002%

    No Known Activations