© 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. 3-GEMMASCOPE-RES-16K
    11. 11364
    Prev
    Next
    INDEX
    Explanations

    specific types of introductory phrases or contextual markers indicating new or noteworthy information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.69
    retudo
    -0.57
    Trayectoria
    -0.54
     EconPapers
    -0.53
    DeleteBehavior
    -0.51
     suena
    -0.50
    Hochspringen
    -0.49
    astify
    -0.49
    SequentialGroup
    -0.49
     actionMode
    -0.49
    POSITIVE LOGITS
     smallest
    0.45
     کوت
    0.41
    osoever
    0.41
    γμα
    0.40
    Larger
    0.40
     widest
    0.39
    GOL
    0.39
    Wider
    0.38
     wider
    0.37
     nyelven
    0.36
    Activations Density 0.242%

    No Known Activations