© 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. 8986
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there."

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

    followed by a capitalized verb

    np_acts-logits-general · gemini-2.0-flash

    there, where, thereafter, therefore

    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
     up
    -0.80
    RenderAtEndOf
    -0.75
     doInBackground
    -0.71
    matchCondition
    -0.68
     contextLoads
    -0.61
    ]='\
    -0.59
    NegativeButton
    -0.58
     Biôgrafia
    -0.57
    PhysRevLett
    -0.57
    CloseOperation
    -0.57
    POSITIVE LOGITS
    ever
    0.99
    fore
    0.98
    FORE
    0.83
    EVER
    0.82
    ther
    0.79
    ver
    0.78
    soever
    0.77
    beit
    0.77
    theless
    0.74
    Ever
    0.73
    Activations Density 0.239%

    No Known Activations