© 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. 101494
    Prev
    Next
    INDEX
    Explanations

    code structure elements related to programming control flow and window management

    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
     gyhoeddwyd
    -0.49
     Normdatei
    -0.48
     censiti
    -0.43
     المعيارى
    -0.42
     Савезне
    -0.42
     Италијани
    -0.41
    GOTREF
    -0.41
    Хьажоргаш
    -0.40
     cab
    -0.40
     validamos
    -0.40
    POSITIVE LOGITS
     finally
    0.53
    finally
    0.48
     aż
    0.47
    providedIn
    0.46
    Eventually
    0.45
    WaitGroup
    0.44
     Dabei
    0.44
    tangentMode
    0.43
     Eventually
    0.42
     schließlich
    0.42
    Activations Density 0.024%

    No Known Activations