© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14854
    Prev
    Next
    INDEX
    Explanations

    JavaScript import statements related to networking and modules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.60
     שוליים
    -0.53
    rungsseite
    -0.51
     RESERVE
    -0.49
     Reserve
    -0.49
    Reserve
    -0.47
    adaptiveStyles
    -0.47
    setzungen
    -0.47
     wheel
    -0.46
     trône
    -0.46
    POSITIVE LOGITS
     client
    4.25
    client
    3.79
     Client
    3.61
    Client
    3.38
     clients
    3.08
     CLIENT
    2.95
    CLIENT
    2.85
     Clients
    2.74
     getClient
    2.50
    Clients
    2.50
    Activations Density 0.185%

    No Known Activations