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. 16-GEMMASCOPE-RES-16K
    6. 5439
    Prev
    Next
    INDEX
    Explanations

    components of advanced materials for biomedical applications

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

    Synthesis or preparation of nanoparticles

    np_acts-logits-general · gemini-2.0-flash

    prepare nanoparticles and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imetsu
    -0.63
    })*/
    -0.61
    withIdentifier
    -0.59
     agrav
    -0.58
    tidase
    -0.57
     кӀ
    -0.56
    ionView
    -0.56
    ">//
    -0.56
    Mitochond
    -0.55
     nephe
    -0.55
    POSITIVE LOGITS
    TintMode
    0.82
     endow
    0.60
     fabricate
    0.58
     Incorporation
    0.58
     hybrid
    0.57
     incorporation
    0.57
     fabri
    0.56
     fabrication
    0.56
    tande
    0.56
     nano
    0.55
    Activations Density 1.895%

    No Known Activations