© 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
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 1341
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to sociopolitical dynamics and actions taken by individuals or institutions

    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
    -0.88
     '\\;'
    -0.82
    AddTagHelper
    -0.79
     nahilalakip
    -0.78
    featureID
    -0.73
     يتيمه
    -0.72
    protoimpl
    -0.69
    SequentialGroup
    -0.68
     betweenstory
    -0.68
     bezeichneter
    -0.67
    POSITIVE LOGITS
     afin
    1.88
     чтобы
    1.86
     כדי
    1.78
    เพื่อ
    1.78
     để
    1.67
     щоб
    1.63
     affinch
    1.62
     เพื่อ
    1.55
     supaya
    1.49
     zodat
    1.38
    Activations Density 3.372%

    No Known Activations