© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1162
    Prev
    Next
    INDEX
    Explanations

    terms related to server and connection settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Legge
    -0.72
     itſelf
    -0.61
     Scissors
    -0.59
     firſt
    -0.59
    ยิ่ง
    -0.58
     ſeveral
    -0.57
     invitation
    -0.57
     partici
    -0.57
     occaf
    -0.56
     ſmall
    -0.56
    POSITIVE LOGITS
    host
    1.73
    Host
    1.65
     Host
    1.65
     host
    1.54
     HOST
    1.46
    HOST
    1.36
    Hosts
    1.29
     Hosts
    1.27
    hosts
    1.27
     hosts
    1.20
    Activations Density 0.073%

    No Known Activations