© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 10089
    Prev
    Next
    INDEX
    Explanations

    conjunctions, specifically variations of the word "but"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.71
    WireFormatLite
    -0.50
     entanto
    -0.49
     packageName
    -0.49
     MMM
    -0.47
     rodriguez
    -0.46
     onBackPressed
    -0.46
    OfWork
    -0.44
    PMS
    -0.44
     tagName
    -0.43
    POSITIVE LOGITS
     poiché
    0.57
     the
    0.54
     ponieważ
    0.50
     it
    0.49
     поскольку
    0.49
     there
    0.48
     poichè
    0.48
     mivel
    0.47
     gdy
    0.47
    nloa
    0.46
    Activations Density 0.226%

    No Known Activations