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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7040
    Prev
    Next
    INDEX
    Explanations

    the use of the word "just" in various contexts

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

    "just" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    just followed by action or description

    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
     kierunku
    -0.51
     Propag
    -0.48
     fieldName
    -0.47
    ragamo
    -0.46
     packageName
    -0.46
     ſol
    -0.46
     PIB
    -0.46
     eventName
    -0.46
     SBI
    -0.46
     rozwój
    -0.46
    POSITIVE LOGITS
    just
    1.61
     just
    1.60
    Just
    1.53
     Just
    1.52
     JUST
    1.48
    JUST
    1.28
     juste
    1.00
     appena
    0.90
    juste
    0.86
     juft
    0.82
    Activations Density 0.099%

    No Known Activations