© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 286
    Prev
    Next
    INDEX
    Explanations

    phrases related to community engagement and collaborative efforts in education

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

    lessons learned from practices

    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
    estimm
    -0.37
     ENTERTAINMENT
    -0.33
    Билгалдахарш
    -0.33
     férias
    -0.32
    mintaan
    -0.32
    UserInput
    -0.32
     CONSUMER
    -0.31
     Consumers
    -0.31
    ništvo
    -0.30
    teenth
    -0.29
    POSITIVE LOGITS
     successes
    0.66
     Infórmanos
    0.65
     cherchés
    0.59
     successful
    0.59
    脚注の使い方
    0.56
    uccess
    0.55
    LookAnd
    0.54
     innovations
    0.54
     inov
    0.54
     proven
    0.54
    Activations Density 0.051%

    No Known Activations