© 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. 41-GEMMASCOPE-RES-16K
    11. 6547
    Prev
    Next
    INDEX
    Explanations

    phrases that express observations about sounds or visuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LIKE
    -0.99
     Like
    -0.95
    Like
    -0.87
     LIKE
    -0.85
    unlike
    -0.84
    Unlike
    -0.82
    Similar
    -0.78
     Unlike
    -0.77
    Such
    -0.74
     unlike
    -0.73
    POSITIVE LOGITS
     like
    0.69
     lượt
    0.48
    Насе
    0.46
     lie
    0.42
     li
    0.42
     kasarigan
    0.41
     Tomorrow
    0.40
     Rema
    0.39
    angg
    0.39
    Verdict
    0.38
    Activations Density 0.146%

    No Known Activations