© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 14264
    Prev
    Next
    INDEX
    Explanations

    terms related to surface characteristics and irregularities in materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ràng
    -0.47
    äfts
    -0.46
     apropri
    -0.45
    calaureate
    -0.45
     Himo
    -0.44
    ึง
    -0.44
    URATION
    -0.43
    ativement
    -0.43
    eryllium
    -0.42
     wią
    -0.42
    POSITIVE LOGITS
    oredCriteria
    0.72
    DockStyle
    0.71
     bumpy
    0.69
     roughness
    0.67
     irregularity
    0.67
     Superhosts
    0.63
     irregularities
    0.61
     surla
    0.61
     imperfections
    0.60
    unknownFields
    0.57
    Activations Density 0.706%

    No Known Activations