© 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. 33-GEMMASCOPE-RES-16K
    11. 4974
    Prev
    Next
    INDEX
    Explanations

    terms related to atomic and molecular structures in materials science

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     setLoading
    -0.36
     tax
    -0.36
    AnimationFrame
    -0.36
    εύ
    -0.35
    bcrypt
    -0.34
     prison
    -0.33
     percentage
    -0.32
     taxation
    -0.32
    дора
    -0.32
     color
    -0.32
    POSITIVE LOGITS
     Surface
    0.88
    Surface
    0.86
     surface
    0.85
    surface
    0.79
     SURFACE
    0.76
     adhesion
    0.74
    表面
    0.72
     Oberflächen
    0.69
    SURFACE
    0.68
    urface
    0.67
    Activations Density 1.527%

    No Known Activations