© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1592
    Prev
    Next
    INDEX
    Explanations

    instances of the word "still" in various contexts, indicating a focus on continuity or persistence

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

    "still"

    np_acts-logits-general · gemini-2.0-flash

    still followed by continuation

    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
     fieldName
    -0.51
     typeName
    -0.50
    HeaderComponent
    -0.50
    openConnection
    -0.49
    ʖ
    -0.48
    forName
    -0.48
     jsonObj
    -0.47
    ToProps
    -0.46
     GBA
    -0.46
    chaun
    -0.46
    POSITIVE LOGITS
    Still
    0.89
    still
    0.85
     Still
    0.83
     STILL
    0.82
     still
    0.79
    STILL
    0.77
    Todavía
    0.65
     tetap
    0.64
     Ainda
    0.59
     ftill
    0.58
    Activations Density 0.074%

    No Known Activations