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. 4-GEMMASCOPE-RES-16K
    6. 727
    Prev
    Next
    INDEX
    Explanations

    medical terms related to renal health and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forests
    -0.94
    Timber
    -0.93
     forest
    -0.92
     timber
    -0.92
     trees
    -0.89
    forests
    -0.88
     Timber
    -0.86
     tree
    -0.84
     Trees
    -0.83
     Forest
    -0.82
    POSITIVE LOGITS
     Renal
    0.75
    SharedDtor
    0.73
     dialysis
    0.73
     Lark
    0.72
    IntentFilter
    0.72
     Sze
    0.71
     Iris
    0.70
    writeFieldEnd
    0.69
    RTEE
    0.68
    ThroughAttribute
    0.66
    Activations Density 4.365%

    No Known Activations