Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68155
    Prev
    Next
    INDEX
    Explanations

    words related to attractions and the concept of attraction itself, often in the context of tourism or interpersonal relations

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

    attraction

    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
    VersionUID
    -0.64
    
    -0.61
    хьтан
    -0.55
    gebob
    -0.55
    DockStyle
    -0.49
     markdown
    -0.49
    pide
    -0.49
    MD
    -0.49
    :✨
    -0.48
     PB
    -0.48
    POSITIVE LOGITS
     attraction
    1.05
     Attraction
    0.91
     atracción
    0.89
     attractions
    0.84
    attraction
    0.84
     attract
    0.77
     Attra
    0.75
    Attra
    0.73
     attra
    0.71
     attracted
    0.71
    Activations Density 0.006%

    No Known Activations