© 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. 20-GEMMASCOPE-RES-16K
    11. 14944
    Prev
    Next
    INDEX
    Explanations

    terms related to keys and locking mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    keys, locks, or combinations

    np_acts-logits-general · gemini-2.0-flash

    keys and locks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regulador
    -0.57
    nosaurus
    -0.57
     trawl
    -0.56
    igslist
    -0.55
    UnitTesting
    -0.55
     dredge
    -0.53
     pinulongan
    -0.52
     alimentaria
    -0.52
    żd
    -0.51
     defoli
    -0.50
    POSITIVE LOGITS
     keys
    1.80
     key
    1.64
     Key
    1.60
     lock
    1.50
     Keys
    1.48
     Locks
    1.45
     locks
    1.45
    Key
    1.43
    Keys
    1.42
    key
    1.39
    Activations Density 0.181%

    No Known Activations