© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 39087
    Prev
    Next
    INDEX
    Explanations

    patterns and structures related to data serialization formats, particularly JSON

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

    <start_of_turn>user

    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
      
    -0.48
    ↵↵
    -0.41
       
    -0.40
        
    -0.38
    ↵
    -0.36
     :
    -0.35
     //
    -0.35
           
    -0.34
     coté
    -0.32
     /
    -0.32
    POSITIVE LOGITS
    <unused14>
    0.90
     imagui
    0.90
    <unused41>
    0.90
    <unused23>
    0.90
    <unused52>
    0.90
    <unused8>
    0.90
    <unused42>
    0.90
    <unused79>
    0.90
    [@BOS@]
    0.89
    <unused16>
    0.89
    Activations Density 0.000%

    No Known Activations