© 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. 20-GEMMASCOPE-RES-131K
    6. 123062
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CompleteListener
    -0.47
     actionTypes
    -0.44
     ſch
    -0.43
    calientes
    -0.42
    tableCell
    -0.41
    SequentialGroup
    -0.40
     purpoſe
    -0.40
    tableLayoutPanel
    -0.40
    rdag
    -0.39
     onAnimation
    -0.38
    POSITIVE LOGITS
     hini
    2.84
     nakalista
    0.72
    
    0.66
     EconPapers
    0.63
    Hentet
    0.61
    httphttps
    0.61
     kasarigan
    0.60
     المعيارى
    0.59
     pinulongan
    0.58
     Waray
    0.58
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.