© 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. 80856
    Prev
    Next
    INDEX
    Explanations

    instances of the word "compliment" and its variations

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

    expressing praise or pleasantness

    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
     veja
    -0.42
     neler
    -0.40
     Dostupné
    -0.39
    JAKARTA
    -0.38
     BIBSYS
    -0.37
     Gea
    -0.36
    setN
    -0.35
     dětí
    -0.35
     prévue
    -0.35
    Bhar
    -0.35
    POSITIVE LOGITS
     compliment
    0.98
     Compli
    0.95
     compliments
    0.93
     complimented
    0.84
    Compli
    0.83
    compli
    0.82
     Complimentary
    0.69
     compli
    0.68
     complimentary
    0.65
    cplusplus
    0.64
    Activations Density 0.006%

    No Known Activations