© 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. 9-GEMMASCOPE-RES-16K
    11. 4349
    Prev
    Next
    INDEX
    Explanations

    the word "been" in various contexts

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

    Follows "have" or "'ve" (or similar words)

    np_acts-logits-general · gemini-2.0-flash

    past participles after been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.72
     ſtate
    -0.65
     ſche
    -0.65
     houſe
    -0.63
     ſch
    -0.60
    <bos>
    -0.60
     purpoſe
    -0.57
     ſtre
    -0.56
     leaſt
    -0.56
    ſelf
    -0.56
    POSITIVE LOGITS
     been
    1.52
    been
    1.35
     Been
    1.29
    Been
    1.23
     BEEN
    1.20
    HasBeen
    0.99
     été
    0.86
     sido
    0.79
     været
    0.74
     geweest
    0.72
    Activations Density 0.167%

    No Known Activations