© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 49330
    Prev
    Next
    INDEX
    Explanations

    specific references to product configurations and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    those or such products/activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vieira
    -0.45
    IConfiguration
    -0.44
     Vikipedi
    -0.42
     Dott
    -0.42
    pump
    -0.42
     pump
    -0.41
     Kano
    -0.40
     approximation
    -0.40
     Mod
    -0.40
    CPtr
    -0.40
    POSITIVE LOGITS
     للمعارف
    0.53
    +#+#
    0.49
    請繼續往下閱讀
    0.48
    Datuak
    0.48
     صوتيه
    0.45
     thereof
    0.44
    ніципалі
    0.43
     للاسماء
    0.43
     المعيارى
    0.41
    SBATCH
    0.41
    Activations Density 0.192%

    No Known Activations