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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5494
    Prev
    Next
    INDEX
    Explanations

    terms related to restoration and recovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionPerformed
    -0.56
     obst
    -0.46
    abstractmethod
    -0.45
    oneofs
    -0.45
     sip
    -0.45
    InstrumentedTest
    -0.44
    firi
    -0.43
     Contribution
    -0.43
    xlarge
    -0.43
     trip
    -0.42
    POSITIVE LOGITS
     restored
    1.33
     restoration
    1.33
     restoring
    1.29
     restore
    1.29
     restores
    1.26
    Restore
    1.17
     Restore
    1.16
    restore
    1.12
     Restoration
    1.09
    Restoration
    1.09
    Activations Density 0.370%

    No Known Activations