© 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. 36-GEMMASCOPE-RES-16K
    11. 5217
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or scripting structures, such as commands and control statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.72
    AndEndTag
    -0.63
     للمعارف
    -0.60
     Bryan
    -0.59
     Fam
    -0.56
     مشين
    -0.56
    PyExc
    -0.56
    BagConstraints
    -0.55
     Cra
    -0.55
    Cra
    -0.55
    POSITIVE LOGITS
     desmotivaciones
    0.49
     vandens
    0.46
     auroit
    0.44
     unterkunft
    0.44
     pouvoit
    0.44
     perfección
    0.42
     faldas
    0.41
     feroit
    0.41
     HttpNotFound
    0.41
     escuelas
    0.40
    Activations Density 0.136%

    No Known Activations