© 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. 33-GEMMASCOPE-RES-16K
    11. 7641
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and judicial terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reverend
    -0.56
     جدًا
    -0.54
     Corporation
    -0.52
     Incorporated
    -0.50
     Brigadier
    -0.49
     cuillère
    -0.48
     television
    -0.47
     Lieutenant
    -0.46
    ًا
    -0.46
     onely
    -0.45
    POSITIVE LOGITS
     Univ
    0.63
     Fig
    0.59
    Univ
    0.59
     např
    0.57
    Fig
    0.57
     fig
    0.56
     Okla
    0.55
     Calif
    0.55
     ppl
    0.54
     Assn
    0.52
    Activations Density 1.281%

    No Known Activations