© 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. 234
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a search for more efficient solutions or choices

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

    method or solution

    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
     Италијани
    -0.38
    setSubject
    -0.35
     nahilalakip
    -0.35
    Становништво
    -0.34
    ItemBackground
    -0.31
     riverside
    -0.30
     taip
    -0.30
    cyklopedia
    -0.30
    tagext
    -0.30
     TableColumn
    -0.30
    POSITIVE LOGITS
     method
    0.64
     método
    0.62
    method
    0.59
     metode
    0.59
     oplossing
    0.57
     metoda
    0.57
    方法
    0.56
    methods
    0.56
     방법
    0.55
     метод
    0.54
    Activations Density 0.080%

    No Known Activations