© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 13653
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to inspiration and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    körper
    -0.76
    amazonaws
    -0.75
    MethodManager
    -0.68
    omaly
    -0.68
     teléfono
    -0.65
    woche
    -0.63
     Barnett
    -0.63
    complexType
    -0.61
    omalies
    -0.61
     body
    -0.60
    POSITIVE LOGITS
     inspiration
    2.20
     inspirations
    2.15
     Inspiration
    2.11
     inspire
    2.01
    Inspiration
    1.97
     inspira
    1.94
     inspires
    1.94
     inspired
    1.93
     inspir
    1.91
     Inspire
    1.86
    Activations Density 0.042%

    No Known Activations