© 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. 22-GEMMASCOPE-RES-16K
    11. 5487
    Prev
    Next
    INDEX
    Explanations

    conjunctions and temporal words indicating conditions or sequences

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

    following "before" or "after."

    np_acts-logits-general · gemini-2.0-flash

    before a subject or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Them
    -0.62
    them
    -0.59
     THEM
    -0.53
    while
    -0.52
     Them
    -0.51
     comigo
    -0.51
     whilst
    -0.50
     bordada
    -0.50
    if
    -0.50
     său
    -0.50
    POSITIVE LOGITS
     they
    2.07
     we
    1.85
     he
    1.46
     you
    1.42
     she
    1.33
     it
    1.23
     there
    1.17
     the
    1.17
     someone
    1.01
    they
    0.97
    Activations Density 0.653%

    No Known Activations