© 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. 3716
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'look' and its variations

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

    "look at" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    look at

    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
    sprechend
    -0.64
    ruptedException
    -0.59
    msgTypes
    -0.59
     Vikipedi
    -0.59
    userdetails
    -0.58
    帖最后由
    -0.58
    stdc
    -0.57
    VersionUID
    -0.57
    hoon
    -0.56
     smtplib
    -0.56
    POSITIVE LOGITS
     at
    1.49
    at
    0.71
    At
    0.66
     tại
    0.63
    ParallelGroup
    0.58
     At
    0.58
     AT
    0.56
     ataca
    0.55
    @
    0.54
     	e
    0.51
    Activations Density 0.137%

    No Known Activations