© 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. 28-GEMMASCOPE-RES-16K
    11. 920
    Prev
    Next
    INDEX
    Explanations

    elements related to decision-making features in applications

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

    that follow periods

    np_acts-logits-general · gemini-2.0-flash

    two or both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    verwijspagina
    -0.75
     الرياضيه
    -0.66
    StoryboardSegue
    -0.62
    ੝
    -0.60
     betweenstory
    -0.59
    المناصب
    -0.58
     ſehr
    -0.56
    хьтан
    -0.56
    PreInfinity
    -0.55
     zwiſchen
    -0.55
    POSITIVE LOGITS
    どちらも
    0.53
     former
    0.53
     Erster
    0.52
     respectively
    0.51
     Both
    0.51
     both
    0.49
     ambas
    0.48
    Both
    0.48
     begge
    0.46
     keduanya
    0.46
    Activations Density 0.834%

    No Known Activations