© 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. 2-GEMMASCOPE-RES-16K
    11. 15543
    Prev
    Next
    INDEX
    Explanations

    references to keys, particularly in technology or control contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    covo
    -0.69
    extAlignment
    -0.66
    ebbe
    -0.66
    twimg
    -0.66
    endgroup
    -0.64
    Zeneca
    -0.61
     convain
    -0.59
    gink
    -0.59
    ContentView
    -0.58
    äfts
    -0.58
    POSITIVE LOGITS
     keys
    3.08
    Keys
    3.02
     Keys
    3.02
    keys
    3.00
     KEYS
    2.53
    KEYS
    2.21
     llaves
    1.36
     chaves
    1.19
     clés
    1.09
     Keyes
    1.06
    Activations Density 0.072%

    No Known Activations