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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 62936
    Prev
    Next
    INDEX
    Explanations

    biological and pharmacological terms related to antibodies and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    awaiter
    -0.40
     or
    -0.35
     getItemCount
    -0.35
     resourceCulture
    -0.31
     parti
    -0.28
    valbard
    -0.28
    archiviato
    -0.28
     oameni
    -0.28
     creditors
    -0.28
     creditor
    -0.28
    POSITIVE LOGITS
    참고
    0.59
    rungsseite
    0.56
    enment
    0.52
    BindingResult
    0.51
    ьажоргаш
    0.51
    észetes
    0.50
     pleaſure
    0.50
     themſelves
    0.50
    RegistryLite
    0.50
    nodoc
    0.49
    Activations Density 0.119%

    No Known Activations