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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 1659
    Prev
    Next
    INDEX
    Explanations

    references to food and beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    öfe
    -0.52
     للمعارف
    -0.51
    zijde
    -0.51
    elemField
    -0.50
    BufferException
    -0.49
    principalColumn
    -0.49
     gezegd
    -0.49
     gewohnt
    -0.49
    NewUrlParser
    -0.49
    :+:
    -0.47
    POSITIVE LOGITS
    存于互联网档案馆
    0.64
     missionaries
    0.62
    ValueStyle
    0.53
     betweenstory
    0.53
     missionary
    0.53
     dikirim
    0.52
    ruptedException
    0.52
     platt
    0.52
    yip
    0.51
    windowFixed
    0.51
    Activations Density 0.264%

    No Known Activations