© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 892
    Prev
    Next
    INDEX
    Explanations

    mentions of knowledge and understanding in various contexts

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

    "knowledge"

    np_acts-logits-general · gemini-2.0-flash

    knowledge transfer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ByUser
    -0.43
    WindowConstants
    -0.40
     Barb
    -0.40
     doubly
    -0.40
     Ferrer
    -0.39
     Solano
    -0.39
     barb
    -0.38
     fig
    -0.38
    fastjson
    -0.37
     STRIP
    -0.37
    POSITIVE LOGITS
    Knowledge
    1.33
     Knowledge
    1.33
     knowledge
    1.32
    knowledge
    1.27
     KNOWLEDGE
    1.20
     conhecimento
    1.00
     conocimiento
    0.98
     pengetahuan
    0.97
    NOWLEDGE
    0.95
     knowled
    0.94
    Activations Density 0.088%

    No Known Activations