© 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. 20-GEMMASCOPE-RES-131K
    11. 42238
    Prev
    Next
    INDEX
    Explanations

    specific names or terms associated with people or characters

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

    HoJos, Ophiucus, Sosa, Vrooder

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ↵
    -0.51
     
    -0.40
    ↵↵
    -0.39
    s
    -0.36
    _
    -0.34
    下
    -0.34
    上
    -0.33
      
    -0.33
    x
    -0.32
        
    -0.32
    POSITIVE LOGITS
     pleaſure
    0.96
     faſt
    0.94
     queſta
    0.91
    iſchen
    0.90
     itſelf
    0.87
    iſche
    0.87
     queſto
    0.85
    ſcher
    0.85
    <unused14>
    0.83
    <unused8>
    0.83
    Activations Density 0.205%

    No Known Activations