© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7463
    Prev
    Next
    INDEX
    Explanations

    emotions or sentiments expressed through small details and nuances in life

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "Small" or "minor" things

    np_acts-logits-general · gemini-2.0-flash

    small, minor, or simple things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     يتيمه
    -0.52
    makeConstraints
    -0.46
    IndentedString
    -0.45
     apellidos
    -0.45
    MemoryWarning
    -0.43
    Portail
    -0.41
    atyw
    -0.38
     pstmt
    -0.37
    DrawerToggle
    -0.37
    豊富な
    -0.36
    POSITIVE LOGITS
     small
    1.60
    small
    1.45
     pequeños
    1.36
     pequenas
    1.35
     piccoli
    1.35
     piccole
    1.34
     tiny
    1.33
     minor
    1.33
     pequenos
    1.32
     pequeñas
    1.29
    Activations Density 0.493%

    No Known Activations