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. 12-GEMMASCOPE-RES-16K
    6. 1355
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential outcomes and possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.80
     Majefty
    -0.79
     Houſe
    -0.71
    AndEndTag
    -0.68
     المعيارى
    -0.68
    ItemLayout
    -0.68
    gameserver
    -0.66
    MessageOf
    -0.64
     eventdata
    -0.64
     متعلقه
    -0.63
    POSITIVE LOGITS
     either
    1.07
    either
    0.86
     or
    0.78
     entweder
    0.68
    ITHER
    0.66
     Either
    0.65
     StatefulWidget
    0.65
    Either
    0.64
     anywhere
    0.63
    不管是
    0.57
    Activations Density 0.479%

    No Known Activations