© 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. 15192
    Prev
    Next
    INDEX
    Explanations

    variants of the word "look" and related expressions indicating consideration or examination

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

    "look" or "looking" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    looking direction or investigation

    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
    ⓧ
    -0.68
    TagMode
    -0.63
    InSection
    -0.58
    tinyos
    -0.58
     mpl
    -0.58
     consuls
    -0.57
    bootstrapcdn
    -0.56
     publice
    -0.55
    Ruj
    -0.54
    posedge
    -0.54
    POSITIVE LOGITS
     forward
    0.90
     back
    0.70
     ahead
    0.66
     positively
    0.65
     toward
    0.65
     favorably
    0.61
     beyond
    0.58
     looking
    0.58
     to
    0.57
     down
    0.56
    Activations Density 0.050%

    No Known Activations