© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 34918
    Prev
    Next
    INDEX
    Explanations

    comparative expressions or phrases indicating preference

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

    comparative

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     XNUMX
    -0.39
    ================
    -0.36
    ReactDOM
    -0.36
    courseId
    -0.35
    Gua
    -0.35
    packageName
    -0.35
    figur
    -0.34
    Lucie
    -0.34
    elfth
    -0.34
     reven
    -0.34
    POSITIVE LOGITS
    より
    1.89
     より
    1.50
    よりも
    1.19
    よりは
    1.14
    보다
    1.01
    により
    0.82
     autorytatywna
    0.78
     otomatig
    0.69
    #+#
    0.61
    Tembelea
    0.61
    Activations Density 0.001%

    No Known Activations