© 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. 119818
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    之
    -0.28
    1
    -0.25
     hôtels
    -0.24
    -
    -0.24
    IM
    -0.24
    COM
    -0.24
     分
    -0.23
    Conclusion
    -0.23
     íntimo
    -0.23
     przeci
    -0.23
    POSITIVE LOGITS
    OGND
    1.13
     invokingState
    0.95
    AddTagHelper
    0.89
     متعلقه
    0.85
     referrerpolicy
    0.85
    évaluateur
    0.83
     Infórmanos
    0.75
     Paglinawan
    0.75
    WriteTagHelper
    0.73
    principalColumn
    0.73
    Activations Density 0.005%

    No Known Activations