© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-GEMMASCOPE-RES-16K
    11. 7047
    Prev
    Next
    INDEX
    Explanations

    terms related to finality or conclusions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vocación
    -0.47
     excelencia
    -0.47
     estándares
    -0.47
     finishes
    -0.43
     humanidade
    -0.43
     signifikan
    -0.42
     justicia
    -0.42
     tradição
    -0.42
     justiça
    -0.42
     relatie
    -0.41
    POSITIVE LOGITS
     final
    2.02
    final
    1.96
    Final
    1.77
     Final
    1.68
     FINAL
    1.64
    FINAL
    1.59
     finale
    1.16
     finales
    1.09
    最終
    1.06
    finals
    1.03
    Activations Density 0.202%

    No Known Activations