© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 55
    Prev
    Next
    INDEX
    Explanations

    variations of the word "look" in different forms and contexts

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

    words related to visual descriptions and appearances

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

    looks like or similar to

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     يتيمه
    -0.73
     palvel
    -0.66
     septum
    -0.61
     concub
    -0.60
     ambiguity
    -0.56
     mobilité
    -0.55
     ambiguities
    -0.55
     servidores
    -0.54
     SafeMath
    -0.54
     Donetsk
    -0.54
    POSITIVE LOGITS
     like
    1.13
     quite
    0.75
    __":
    0.73
     very
    0.63
     somewhat
    0.63
     similar
    0.61
    __':
    0.60
     unlike
    0.60
     much
    0.60
     almost
    0.60
    Activations Density 0.044%

    No Known Activations