© 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. 1132
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking techniques and preparation steps

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

    Followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    appropriately placed into

    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
    InvalidProtocol
    -0.64
     متعلقه
    -0.61
    ďaka
    -0.59
    LookAnd
    -0.54
     unprecedented
    -0.54
     Offisielt
    -0.53
     infeliz
    -0.51
    enseignements
    -0.51
     dermed
    -0.49
     nemlig
    -0.49
    POSITIVE LOGITS
     preferably
    1.11
     suitable
    1.03
     appropriate
    1.00
    preferably
    0.99
     geeigne
    0.87
     suitably
    0.85
     reputable
    0.84
     decent
    0.84
    appropriate
    0.84
     подходя
    0.83
    Activations Density 0.327%

    No Known Activations