© 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. 1-GEMMASCOPE-RES-16K
    11. 11633
    Prev
    Next
    INDEX
    Explanations

    references to "bare" entities or conditions, particularly in physical or anatomical contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    zzleHttp
    -0.48
    webElementXpaths
    -0.47
    Personendaten
    -0.47
    tagHelperRunner
    -0.46
    الحياه
    -0.43
     billet
    -0.43
    ugc
    -0.43
    頭を
    -0.42
     Nod
    -0.42
    ništ
    -0.42
    POSITIVE LOGITS
     bare
    0.64
     useState
    0.62
     naked
    0.56
     shorts
    0.55
    Einzelnachweise
    0.54
     GenerationType
    0.53
    Setter
    0.52
     kaynağından
    0.51
    참고
    0.50
    naked
    0.49
    Activations Density 0.371%

    No Known Activations