© 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. 20-GEMMASCOPE-RES-16K
    11. 3344
    Prev
    Next
    INDEX
    Explanations

    references to tasks or actions that have been completed or are being undertaken

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

    phrases with verbs like "do", "done", or "doing" followed by other words.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     magnétique
    -0.52
     législation
    -0.51
    garek
    -0.49
     bahía
    -0.47
     Câmara
    -0.46
     considération
    -0.46
     transparencia
    -0.45
     térm
    -0.45
     pauvreté
    -0.45
     traseira
    -0.44
    POSITIVE LOGITS
     Done
    1.13
     done
    1.10
     DONE
    1.02
    done
    1.00
    Done
    0.97
    Doing
    0.95
    doing
    0.94
     Doing
    0.93
     doings
    0.87
    DONE
    0.84
    Activations Density 0.141%

    No Known Activations