© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 670
    Prev
    Next
    INDEX
    Explanations

    names, particularly those that might refer to individuals or locations in Asia

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

    chinese place and personal names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StandardCharsets
    -0.59
     समीक्षक
    -0.57
     beginnetje
    -0.57
    RTLI
    -0.55
    OCCURRED
    -0.52
    PerformLayout
    -0.51
    +#+
    -0.49
    eniendo
    -0.49
    :+:
    -0.49
     femininas
    -0.49
    POSITIVE LOGITS
     Logement
    0.39
    ante
    0.35
    TypedDataSet
    0.35
    
    0.35
     Selig
    0.35
     nawr
    0.35
     ivelany
    0.34
    Enllaces
    0.34
     Italijanski
    0.34
    Kanpo
    0.34
    Activations Density 0.031%

    No Known Activations