© 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. 56052
    Prev
    Next
    INDEX
    Explanations

    words related to charm and attractiveness

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

    allure and enchantment

    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
    endregion
    -0.57
     Livermore
    -0.49
    MediaStore
    -0.47
     Widodo
    -0.45
     Quo
    -0.44
     FED
    -0.44
     Stadia
    -0.43
     Lordship
    -0.43
    FDRE
    -0.41
     Tundra
    -0.41
    POSITIVE LOGITS
     charm
    1.03
    Charming
    0.99
     Charm
    0.98
     Charming
    0.93
     charme
    0.93
    Charm
    0.91
    charming
    0.90
    charm
    0.89
     charming
    0.88
     charmed
    0.87
    Activations Density 0.002%

    No Known Activations