© 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. 37-GEMMASCOPE-RES-16K
    11. 3937
    Prev
    Next
    INDEX
    Explanations

    elements that indicate scholarly research and detailed analysis of scientific questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Table
    -0.46
     countless
    -0.44
     Wikiseite
    -0.43
     costuma
    -0.42
    mentioned
    -0.42
     tampoco
    -0.42
     mentioned
    -0.41
     confund
    -0.40
     suele
    -0.40
    matchCondition
    -0.40
    POSITIVE LOGITS
     novel
    0.69
     впервые
    0.64
    rungsseite
    0.61
     впер
    0.61
    novel
    0.61
     herein
    0.57
     erstmal
    0.54
     erstmals
    0.54
    首次
    0.53
    Novel
    0.52
    Activations Density 1.979%

    No Known Activations