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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8633
    Prev
    Next
    INDEX
    Explanations

    phrases indicating additional information or transition in thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.73
     HttpNotFound
    -0.62
    sertation
    -0.62
    BibitemShut
    -0.59
    featureID
    -0.57
     MTC
    -0.57
    征詢我
    -0.57
    ⪜
    -0.57
     dissertation
    -0.57
    phosa
    -0.56
    POSITIVE LOGITS
     Wikiseite
    0.43
    Pautan
    0.40
     paraître
    0.39
     geçi
    0.37
     dévelo
    0.36
     kullanılan
    0.36
     diatur
    0.36
     betroffen
    0.35
     gyak
    0.34
    XCTAssert
    0.34
    Activations Density 0.549%

    No Known Activations