© 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. 38-GEMMASCOPE-RES-16K
    11. 8905
    Prev
    Next
    INDEX
    Explanations

    elements related to social events and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.56
    Promoting
    -0.51
    Providing
    -0.49
     behulp
    -0.49
    Creating
    -0.48
    producing
    -0.48
    ftagPool
    -0.47
    providing
    -0.47
    creating
    -0.46
     Producing
    -0.45
    POSITIVE LOGITS
     seeing
    2.25
     hearing
    2.16
    seeing
    1.79
    Seeing
    1.73
     Seeing
    1.71
    hearing
    1.69
     noticing
    1.63
    Hearing
    1.59
     witnessing
    1.55
     Hearing
    1.54
    Activations Density 0.733%

    No Known Activations