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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 68236
    Prev
    Next
    INDEX
    Explanations

    references to supportive environments and care

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

    supportive environment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jet
    -0.49
     centralization
    -0.49
     personalization
    -0.49
     consecration
    -0.49
    reditation
    -0.49
     randomization
    -0.49
    CURY
    -0.49
     rheumatism
    -0.48
     استنادى
    -0.47
     standardization
    -0.47
    POSITIVE LOGITS
     supportive
    1.91
    ortive
    1.34
     Supp
    0.97
    Supp
    0.86
     supporter
    0.81
     suppor
    0.79
    supp
    0.75
    helpful
    0.74
    protective
    0.73
     helpful
    0.72
    Activations Density 0.004%

    No Known Activations