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. 24-GEMMASCOPE-RES-16K
    6. 2316
    Prev
    Next
    INDEX
    Explanations

    chemical interactions and bonding phenomena in molecular structures

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

    Chemical functional groups

    np_acts-logits-general · gemini-2.0-flash

    chemical functional groups and linkages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cesse
    -0.61
    ỡng
    -0.52
     Vlas
    -0.51
    Brief
    -0.50
     collectionView
    -0.50
    Personendaten
    -0.49
    Reply
    -0.49
     compila
    -0.49
     CreateTagHelper
    -0.48
     zä
    -0.47
    POSITIVE LOGITS
     oxygen
    0.73
     terminal
    0.67
     attached
    0.67
     Sauerstoff
    0.62
     bond
    0.61
     ddelweddau
    0.60
     substitu
    0.58
     carbons
    0.58
     carbon
    0.58
     linkage
    0.58
    Activations Density 1.014%

    No Known Activations