© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14986
    Prev
    Next
    INDEX
    Explanations

    the word "there."

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

    "there" followed by a form of "to be"

    np_acts-logits-general · gemini-2.0-flash

    existence statements with "there"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    PS
    -0.38
    <eos>
    -0.37
     Forst
    -0.37
    PCA
    -0.37
     via
    -0.36
    AP
    -0.36
    SP
    -0.36
    PJ
    -0.35
    pS
    -0.35
    syl
    -0.35
    POSITIVE LOGITS
     there
    0.71
     propOrder
    0.70
    there
    0.68
     noDo
    0.65
     ſeine
    0.65
     CreateTagHelper
    0.65
     CanadaChoose
    0.63
     wireType
    0.63
     nonUne
    0.63
    There
    0.61
    Activations Density 0.141%

    No Known Activations