© 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. 108
    Prev
    Next
    INDEX
    Explanations

    references to legal issues and claims

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

    pronoun followed by verb

    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
     approach
    -0.43
    WEL
    -0.38
     followed
    -0.34
     phải
    -0.33
     therefore
    -0.32
     method
    -0.32
     compelled
    -0.32
     should
    -0.32
     следует
    -0.32
     subsequent
    -0.31
    POSITIVE LOGITS
     CreateTagHelper
    0.88
    MLLoader
    0.78
    transQ
    0.72
     EconPapers
    0.71
    AutoScaleMode
    0.70
    
    0.67
    Personendaten
    0.67
    protoimpl
    0.66
     kasarigan
    0.63
    awtextra
    0.61
    Activations Density 0.046%

    No Known Activations