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-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 2898
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to bonding and adhesion in materials, particularly in a medical or dental context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     greateſt
    -0.97
     pleaſure
    -0.89
    Personensuche
    -0.87
     Diſ
    -0.85
     Inſ
    -0.85
     Eſ
    -0.84
     Reſ
    -0.83
    expandindo
    -0.82
     Monfieur
    -0.82
     betweenstory
    -0.81
    POSITIVE LOGITS
     bond
    1.47
     bonds
    1.45
     Bond
    1.42
    bond
    1.42
    bonds
    1.39
     Bonds
    1.37
    Bond
    1.30
     BOND
    1.29
     bonding
    1.14
    Bonds
    1.14
    Activations Density 0.177%

    No Known Activations