© 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. 9312
    Prev
    Next
    INDEX
    Explanations

    the repeated usage of the word "must" indicating necessity or obligation

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

    "must"

    np_acts-logits-general · gemini-2.0-flash

    obligation or necessity

    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
     Schie
    -0.56
    overview
    -0.51
    figure
    -0.50
    idea
    -0.48
     ideia
    -0.48
     Tiefen
    -0.45
    eaway
    -0.43
    <bos>
    -0.43
    krie
    -0.43
     chiếu
    -0.43
    POSITIVE LOGITS
     must
    1.83
     Must
    1.73
    Must
    1.66
    must
    1.66
     MUST
    1.45
    MUST
    1.42
    必须
    1.02
     måste
    1.02
     muſt
    1.01
     muft
    0.97
    Activations Density 0.122%

    No Known Activations