© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10785
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of doubt or disbelief

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

    "do" or "does" as an auxiliary verb

    np_acts-logits-general · gemini-2.0-flash

    do not / does not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soient
    -0.57
    richTextPanel
    -0.57
    Be
    -0.54
    ArrowToggle
    -0.53
    webElementXpaths
    -0.53
    SequentialGroup
    -0.53
    ientôt
    -0.51
    RenderAtEndOf
    -0.51
    ंदीखरीदारी
    -0.50
    ChildScrollView
    -0.50
    POSITIVE LOGITS
     belong
    0.85
     want
    0.84
     need
    0.84
     have
    0.82
     deserve
    0.80
     exist
    0.78
     seem
    0.73
     require
    0.67
     tend
    0.66
     owe
    0.66
    Activations Density 0.253%

    No Known Activations