© 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. 7-GEMMASCOPE-RES-16K
    11. 15456
    Prev
    Next
    INDEX
    Explanations

    references to knowledge and understanding in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.45
     Ferrer
    -0.40
    boven
    -0.40
    bleau
    -0.40
    fastjson
    -0.40
     bridesmaid
    -0.40
    Kommentare
    -0.38
    бовал
    -0.38
    Datenschutz
    -0.38
     besonder
    -0.38
    POSITIVE LOGITS
     knowledge
    2.78
     Knowledge
    2.59
    Knowledge
    2.56
    knowledge
    2.50
     KNOWLEDGE
    2.30
     conocimiento
    1.88
     conhecimento
    1.82
     pengetahuan
    1.78
     knowled
    1.70
     connaissances
    1.70
    Activations Density 0.089%

    No Known Activations