© 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. 34-GEMMASCOPE-RES-16K
    11. 10586
    Prev
    Next
    INDEX
    Explanations

    references to authoritative figures or entities associated with governance or administration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.82
    parsedMessage
    -0.75
    出版年
    -0.65
    Filmografie
    -0.65
     HttpNotFound
    -0.64
    المناصب
    -0.58
    featureID
    -0.57
    merking
    -0.56
    ngrx
    -0.56
    complexContent
    -0.56
    POSITIVE LOGITS
     company
    1.29
    company
    1.06
     compañía
    0.85
    Company
    0.84
     agency
    0.79
    公司
    0.79
     COMPANY
    0.78
     Company
    0.78
     organisation
    0.76
     instituição
    0.75
    Activations Density 1.299%

    No Known Activations