© 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. 2-GEMMASCOPE-RES-16K
    11. 8451
    Prev
    Next
    INDEX
    Explanations

    HTML or web-related elements, specifically links and stylesheets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    -0.63
     surla
    -0.60
     saveiro
    -0.55
     PeEnEo
    -0.54
    bufio
    -0.52
    EndGlobalSection
    -0.52
     pleaſure
    -0.50
    انجليز
    -0.50
    specifically
    -0.49
    kháu
    -0.49
    POSITIVE LOGITS
     rel
    0.52
     min
    0.44
     laikā
    0.39
     end
    0.38
    ншни
    0.37
    ends
    0.36
     ______
    0.36
     _____
    0.36
     Воз
    0.35
     ____
    0.35
    Activations Density 0.079%

    No Known Activations