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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8324
    Prev
    Next
    INDEX
    Explanations

    references to museums or museum-related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slightly
    -0.45
     slight
    -0.45
    AsUp
    -0.42
     tenacious
    -0.41
    CompleteListener
    -0.40
    enumii
    -0.40
     Ame
    -0.38
    anum
    -0.38
    cách
    -0.38
     ‹
    -0.38
    POSITIVE LOGITS
     list
    0.78
    list
    0.77
    ſelves
    0.56
    cellation
    0.55
     itſelf
    0.52
     pleaſure
    0.52
    ChildScrollView
    0.51
     Museum
    0.51
    ſelf
    0.51
    List
    0.50
    Activations Density 0.137%

    No Known Activations