© 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. 971
    Prev
    Next
    INDEX
    Explanations

    relationships and connections between entities

    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
     every
    -0.75
     Every
    -0.74
    Every
    -0.73
    every
    -0.69
     ogni
    -0.45
     setiap
    -0.45
     EVERY
    -0.42
    ทุก
    -0.40
     varje
    -0.39
     elke
    -0.38
    POSITIVE LOGITS
     eachother
    1.86
     друг
    1.80
     varandra
    1.78
     nhau
    1.77
     elkaar
    1.65
    彼此
    1.46
     einander
    1.45
    กัน
    1.38
     mutual
    1.34
    お互
    1.30
    Activations Density 0.326%

    No Known Activations