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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 13446
    Prev
    Next
    INDEX
    Explanations

    terms related to inner ear structure and hearing disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaynağından
    -0.66
     writeTo
    -0.51
    PhysRevLett
    -0.50
    vedev
    -0.49
    bed
    -0.48
    msgTypes
    -0.48
    Източници
    -0.47
    ModelState
    -0.47
    CommandText
    -0.47
     rú
    -0.47
    POSITIVE LOGITS
     ear
    1.52
     ears
    1.42
     hearing
    1.36
     Hearing
    1.31
    Hearing
    1.21
     deafness
    1.18
     deaf
    1.16
     Ears
    1.16
    hearing
    1.16
     Ear
    1.15
    Activations Density 0.327%

    No Known Activations