© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119836
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or parameters in programming and mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    PageModule
    -0.41
    storm
    -0.39
    furter
    -0.39
    पया
    -0.38
    inser
    -0.37
    swag
    -0.37
     SIMBAD
    -0.36
     reme
    -0.36
    ]")]
    -0.36
     sessionFactory
    -0.35
    POSITIVE LOGITS
    httphttps
    0.60
     חיצוניים
    0.50
    abestanden
    0.50
     ktorí
    0.44
    tagHelperRunner
    0.42
    Rujuakan
    0.41
    лтемелер
    0.41
    цездатний
    0.41
    脚注の使い方
    0.40
     محفوظة
    0.40
    Activations Density 0.413%

    No Known Activations