© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 54430
    Prev
    Next
    INDEX
    Explanations

    language related to negation and reduction regarding various topics, particularly in health and wellbeing contexts

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

    reduce, prevent, decrease

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ब्रेकडाउन
    -0.48
     herself
    -0.35
    连
    -0.33
     met
    -0.33
     насељу
    -0.32
     autorytatywna
    -0.32
    bootstrapcdn
    -0.31
    să
    -0.31
    ürme
    -0.31
     chief
    -0.30
    POSITIVE LOGITS
    AndEndTag
    0.62
    tonode
    0.58
    genodigd
    0.56
     bambú
    0.53
    ロウィン
    0.52
     चीज़ों
    0.52
    RemoveField
    0.50
    Архівовано
    0.50
    omiast
    0.49
    原始内容存档于
    0.48
    Activations Density 0.026%

    No Known Activations