© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101287
    Prev
    Next
    INDEX
    Explanations

    sentences that reflect dialogue or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.49
    
    -0.47
    inally
    -0.47
     '\\;'
    -0.47
     ModelRenderer
    -0.47
     îna
    -0.46
    請繼續往下閱讀
    -0.45
    今後も
    -0.45
    ](#
    -0.45
     termica
    -0.45
    POSITIVE LOGITS
    ########.
    0.57
    SOUNDBITE
    0.50
    providedIn
    0.41
    Succeed
    0.35
     Exactos
    0.35
    Lähteet
    0.34
    Younger
    0.34
     jspb
    0.34
    AfterClass
    0.33
    ttää
    0.33
    Activations Density 0.018%

    No Known Activations