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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 7251
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and conditions involving the diaphragm and abdominal organs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    เคร
    -0.58
     mandibular
    -0.55
    melho
    -0.55
     nozzles
    -0.53
     zirc
    -0.53
     toothbrush
    -0.51
     mandible
    -0.49
     branche
    -0.49
     Barnet
    -0.48
     cory
    -0.47
    POSITIVE LOGITS
    styleType
    0.80
     Fluid
    0.78
     fluid
    0.77
     pleural
    0.74
    AddTagHelper
    0.74
     peritoneal
    0.71
    JspWriter
    0.68
    Fluid
    0.67
     Ple
    0.66
    fluid
    0.64
    Activations Density 0.656%

    No Known Activations