© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15766
    Prev
    Next
    INDEX
    Explanations

    references to various government departments

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

    institutional affiliations and departmental addresses in academic and official documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    raulic
    -0.47
     ddelwed
    -0.45
    complexContent
    -0.43
    ſſung
    -0.43
    原始内容存档
    -0.43
     ainfi
    -0.42
     sàng
    -0.42
    原始内容存档于
    -0.41
    esez
    -0.41
     exciter
    -0.41
    POSITIVE LOGITS
     department
    0.91
    department
    0.90
    Department
    0.88
     departmental
    0.86
     Department
    0.86
    artment
    0.84
    DEPARTMENT
    0.82
     Departmental
    0.82
     Departments
    0.81
     departments
    0.79
    Activations Density 0.093%

    No Known Activations