© 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. 35-GEMMASCOPE-RES-16K
    11. 10302
    Prev
    Next
    INDEX
    Explanations

    terms that indicate customization and meeting specific needs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Доб
    -0.46
     Paglinawan
    -0.46
    SuspendLayout
    -0.40
    Poss
    -0.37
     shad
    -0.36
    رشف
    -0.36
    tinyos
    -0.35
     indruk
    -0.35
    subplots
    -0.35
    dération
    -0.35
    POSITIVE LOGITS
     needs
    2.50
     requirements
    2.17
    needs
    2.11
     Needs
    2.05
     demands
    1.97
     necesidades
    1.93
    Needs
    1.91
    requirements
    1.90
    需求
    1.85
     kebutuhan
    1.84
    Activations Density 0.596%

    No Known Activations