© 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. 13042
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of a document or section

    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
    reactstrap
    -0.54
    skjaer
    -0.53
    ContentLoaded
    -0.52
    SequentialGroup
    -0.52
    patine
    -0.52
    äsident
    -0.49
    artifactId
    -0.49
    tocin
    -0.48
    Autoritní
    -0.48
    gebob
    -0.48
    POSITIVE LOGITS
     three
    1.24
     two
    1.10
     Three
    1.05
     four
    1.05
     THREE
    1.03
    three
    1.02
    Three
    1.00
     five
    0.95
     trois
    0.94
     drei
    0.94
    Activations Density 0.421%

    No Known Activations