© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7684
    Prev
    Next
    INDEX
    Explanations

    criteria and outcomes related to medical procedures and their evaluations

    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
    verket
    -0.41
     healthcare
    -0.39
     physician
    -0.39
     lab
    -0.37
     heart
    -0.36
     clinician
    -0.36
     LABORATORY
    -0.36
     prod
    -0.35
     doctor
    -0.35
     medical
    -0.35
    POSITIVE LOGITS
     postoperative
    0.68
     preoperative
    0.59
    術
    0.53
     術
    0.52
    enumii
    0.51
     surgeons
    0.50
    ArgumentParser
    0.48
     متعلقه
    0.48
    术
    0.48
    UnsafeEnabled
    0.48
    Activations Density 1.808%

    No Known Activations