© 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 - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 1004
    Prev
    Next
    INDEX
    Explanations

    instances of the word "final."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     venezolano
    -0.43
    kko
    -0.42
    ouna
    -0.40
     munc
    -0.39
    🔕
    -0.39
    cripciones
    -0.38
     ciudadano
    -0.38
    âneo
    -0.38
    inscrire
    -0.38
     Erziehung
    -0.38
    POSITIVE LOGITS
     final
    4.25
    final
    3.77
    Final
    3.75
     Final
    3.75
     FINAL
    3.52
    FINAL
    3.23
    最終
    2.23
     finalize
    2.23
     finais
    2.22
     finale
    2.17
    Activations Density 0.114%

    No Known Activations