© 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. 27-GEMMASCOPE-RES-16K
    11. 8985
    Prev
    Next
    INDEX
    Explanations

    sentences that convey insights or realizations about personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    knowing
    -0.49
    Хьажоргаш
    -0.49
     sabemos
    -0.48
     knowing
    -0.48
     sappiamo
    -0.47
    Rohy
    -0.47
    tamol
    -0.47
     known
    -0.47
    Known
    -0.46
     cherchés
    -0.45
    POSITIVE LOGITS
     actually
    0.81
    原來
    0.79
    原来
    0.77
     ternyata
    0.72
    actually
    0.71
    Actually
    0.60
     indeed
    0.57
     Actually
    0.57
    其實
    0.56
    実は
    0.56
    Activations Density 0.446%

    No Known Activations