Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11105
    Prev
    Next
    INDEX
    Explanations

    terms related to surgical procedures and postoperative care

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Postoperative care and recovery

    np_acts-logits-general · gemini-2.0-flash

    postoperative patient recovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.54
    ceral
    -0.54
    >");
    
    -0.52
     cứu
    -0.52
    rrggbb
    -0.52
     gyhoeddwyd
    -0.51
    Mvh
    -0.49
    CGContext
    -0.49
    lexia
    -0.49
     springfox
    -0.48
    POSITIVE LOGITS
     postoperative
    0.87
     dressings
    0.71
     recovery
    0.67
     rest
    0.64
     resting
    0.64
     reposo
    0.64
     discharge
    0.63
     dressing
    0.62
     bed
    0.62
     patient
    0.61
    Activations Density 0.536%

    No Known Activations