© 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. 10-GEMMASCOPE-RES-16K
    11. 16198
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate finality or the last instances of events or people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.48
     wireType
    -0.48
    المناصب
    -0.45
    gao
    -0.45
     ✭✭
    -0.45
    aneously
    -0.44
     Hera
    -0.43
    bable
    -0.43
     IFTT
    -0.42
    isses
    -0.41
    POSITIVE LOGITS
     last
    1.09
     final
    1.03
    Final
    1.02
     FINAL
    1.00
     Final
    1.00
     LAST
    0.93
    FINAL
    0.93
     posled
    0.92
    Last
    0.91
    last
    0.91
    Activations Density 0.471%

    No Known Activations