© 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. 8559
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms related to guides

    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
    XmlIgnore
    -0.59
    prefixer
    -0.55
    ArgumentParser
    -0.53
     Lindley
    -0.53
    stylers
    -0.52
     Niki
    -0.51
     propOrder
    -0.50
     Dumont
    -0.48
     SKS
    -0.47
    ftagPool
    -0.46
    POSITIVE LOGITS
     Kea
    1.05
    Dea
    1.03
     Dea
    1.02
    eak
    1.02
    rea
    1.02
    Rea
    1.02
     Rea
    1.00
     Cea
    1.00
    ea
    0.99
     Nea
    0.96
    Activations Density 0.672%

    No Known Activations