© 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. 1345
    Prev
    Next
    INDEX
    Explanations

    references to geographical regions and their respective nutritional or culinary contexts

    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
    IsMutable
    -0.39
    
    -0.36
    stdc
    -0.33
    ือน
    -0.32
     nahilalakip
    -0.31
    ungkan
    -0.31
    舺
    -0.31
     totul
    -0.31
    ervlak
    -0.30
     Māori
    -0.30
    POSITIVE LOGITS
     Arab
    1.52
     Arabic
    1.35
    Arab
    1.35
     Arabs
    1.30
     arab
    1.27
     ARAB
    1.27
     Middle
    1.23
     Arabian
    1.23
     Jordanian
    1.21
     Syrian
    1.16
    Activations Density 0.310%

    No Known Activations