© 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. 31-GEMMASCOPE-RES-16K
    11. 11147
    Prev
    Next
    INDEX
    Explanations

    variations of the word "finish," including different forms such as "finishing," "finished," and "finishers."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "finishing" or its variations (like "finisher", "finished").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.48
     vectorielle
    -0.45
    verwijspagina
    -0.43
     krwi
    -0.42
    vacy
    -0.42
     financieras
    -0.41
    tır
    -0.41
     financières
    -0.40
     disant
    -0.40
    wieś
    -0.40
    POSITIVE LOGITS
    finish
    0.90
     FINISH
    0.88
     finish
    0.88
     Finish
    0.87
     Finished
    0.87
    FINISH
    0.83
    Finish
    0.77
     finished
    0.77
     Finishing
    0.76
    finished
    0.75
    Activations Density 0.103%

    No Known Activations