© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 4709
    Prev
    Next
    INDEX
    Explanations

    references to crystal structures and their classifications

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

    Crystal structures and crystallization

    np_acts-logits-general · gemini-2.0-flash

    crystal structure

    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
    AddTagHelper
    -0.64
    Hozzáférés
    -0.64
    !*\
    -0.63
    enterOuterAlt
    -0.62
    DeleteBehavior
    -0.59
     mourut
    -0.55
    SharedCtor
    -0.55
    routeProvider
    -0.54
     Fati
    -0.54
     Loa
    -0.53
    POSITIVE LOGITS
     crystal
    1.41
     Crystal
    1.36
     crystals
    1.27
    Crystal
    1.25
    crystal
    1.24
     Crystals
    1.12
     cristal
    1.03
     Cryst
    1.01
     kristal
    0.99
     krist
    0.95
    Activations Density 0.114%

    No Known Activations