© 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. 21-GEMMASCOPE-RES-16K
    11. 10535
    Prev
    Next
    INDEX
    Explanations

    references to Android app components and coding structures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    makeText
    -0.31
    Pyx
    -0.31
    gather
    -0.29
    appBar
    -0.29
     pain
    -0.29
    begre
    -0.29
    notice
    -0.29
    Autowired
    -0.29
     قرب
    -0.28
    ỏa
    -0.28
    POSITIVE LOGITS
    MLLoader
    0.89
    StoryboardSegue
    0.88
    FragmentManager
    0.83
     Fragment
    0.74
    Fragment
    0.73
    DialogFragment
    0.73
    WriteTagHelper
    0.73
     ویکی‌پدی
    0.70
     onCreateView
    0.64
    setArguments
    0.63
    Activations Density 0.094%

    No Known Activations