© 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. 9-GEMMASCOPE-RES-131K
    11. 99397
    Prev
    Next
    INDEX
    Explanations

    references to content-type metadata in HTML documents

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

    content definition

    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
    RegressionTest
    -0.38
    NSYLVANIA
    -0.37
    цезда
    -0.34
     disponibilités
    -0.33
    HomeAsUp
    -0.32
     deiner
    -0.31
    Siehe
    -0.30
    StreetMap
    -0.30
     invokevirtual
    -0.29
    ',['
    -0.28
    POSITIVE LOGITS
     content
    1.95
     Content
    1.56
    content
    1.56
     CONTENT
    1.55
    Content
    1.40
    CONTENT
    1.35
     contenido
    1.26
     conteúdo
    1.23
     contenu
    1.21
    ontent
    1.21
    Activations Density 0.004%

    No Known Activations