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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10041
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to structural characterization and analysis methods in materials science

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

    Methods of structural characterization

    np_acts-logits-general · gemini-2.0-flash

    X-ray diffraction and TEM analysis

    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
    ArgumentParser
    -0.74
    MENAFN
    -0.60
    TintMode
    -0.57
    resave
    -0.57
     JpaRepository
    -0.56
    PerformLayout
    -0.54
    ostoma
    -0.54
     FormGroup
    -0.53
     AIAA
    -0.52
    ObjectContext
    -0.51
    POSITIVE LOGITS
     X
    0.65
    getX
    0.55
     XRD
    0.54
     dif
    0.53
     kır
    0.52
     inelastic
    0.52
     diffuse
    0.52
     powder
    0.51
    diff
    0.51
    RIX
    0.49
    Activations Density 0.713%

    No Known Activations