© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 39036
    Prev
    Next
    INDEX
    Explanations

    words related to negative assertions or prohibitions

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

    donates, donates, donning, don't, doesn't

    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
     ujednoznacz
    -0.82
    protoimpl
    -0.82
     ब्रेकडाउन
    -0.79
     للمعارف
    -0.78
     utafitiHapana
    -0.77
    存于互联网档案馆
    -0.76
     Wikimedijinoj
    -0.75
    PyExc
    -0.73
     protoimpl
    -0.71
     kaynağından
    -0.71
    POSITIVE LOGITS
     can
    0.38
     Do
    0.37
     weren
    0.35
     Can
    0.35
     wasn
    0.35
     Didn
    0.33
     aren
    0.33
     didn
    0.33
     Don
    0.33
     do
    0.32
    Activations Density 0.039%

    No Known Activations