© 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. 9-GEMMASCOPE-RES-131K
    11. 128603
    Prev
    Next
    INDEX
    Explanations

    references to namespaces in the code

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

    C++ namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     húmedo
    -0.30
     spectateurs
    -0.29
    UnusedPrivate
    -0.28
    눠
    -0.27
     automáticamente
    -0.26
     poitrine
    -0.25
    ilaian
    -0.24
    மை
    -0.24
    Président
    -0.24
     capuche
    -0.23
    POSITIVE LOGITS
    ValueStyle
    0.92
    Portail
    0.84
    endphp
    0.84
    namespace
    0.83
    Portale
    0.82
    хьтан
    0.78
    脚注の使い方
    0.77
     namespace
    0.76
    didSet
    0.76
     surla
    0.75
    Activations Density 0.006%

    No Known Activations