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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 11867
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific contexts or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obicei
    -0.59
     gewöhnlich
    -0.56
    parsedMessage
    -0.55
    TypedDataSet
    -0.51
     zufolge
    -0.50
    ähteet
    -0.50
    CppCodeGen
    -0.50
    ]-'
    -0.49
     Schluß
    -0.46
     ſte
    -0.45
    POSITIVE LOGITS
     within
    2.00
    Within
    1.98
    within
    1.97
     Within
    1.92
     WITHIN
    1.84
     dentro
    1.47
    Dentro
    1.46
     innerhalb
    1.43
     Dentro
    1.39
    dentro
    1.35
    Activations Density 0.163%

    No Known Activations