© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3694
    Prev
    Next
    INDEX
    Explanations

    references to power and energy-related topics

    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
    Personensuche
    -0.99
    Rüyada
    -0.96
     Jams
    -0.95
     дописавши
    -0.95
     betweenstory
    -0.90
     diphtheria
    -0.90
    Parcelize
    -0.90
     Monks
    -0.90
     doubtnut
    -0.89
     للاسماء
    -0.88
    POSITIVE LOGITS
     Power
    2.13
     power
    2.09
    Power
    2.02
    power
    1.93
    POWER
    1.88
     POWER
    1.84
     Powers
    1.72
     powers
    1.69
    powers
    1.66
    Powers
    1.59
    Activations Density 0.048%

    No Known Activations