© 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. 38334
    Prev
    Next
    INDEX
    Explanations

    instances of the term "non" or related words indicating negation or absence

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

    words with non- prefix

    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
     BrowserModule
    -0.37
     pleaſure
    -0.37
    iesa
    -0.36
     дописавши
    -0.35
    GEBURTSDATUM
    -0.35
    PlaceHolder
    -0.34
    hela
    -0.33
    TagMode
    -0.33
     meisje
    -0.33
     képes
    -0.32
    POSITIVE LOGITS
    NON
    2.03
    Non
    1.87
    non
    1.82
     NON
    1.79
     Non
    1.77
     non
    1.53
    非
    1.15
    ノン
    1.10
    nons
    1.07
     非
    1.06
    Activations Density 0.024%

    No Known Activations