© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4650
    Prev
    Next
    INDEX
    Explanations

    the word "which" in various contexts and its associated attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.71
     ――――
    -0.68
    ImageContext
    -0.67
     myſelf
    -0.65
     Efq
    -0.63
    expandindo
    -0.62
    FieldBuilder
    -0.61
     mergeFrom
    -0.60
     intest
    -0.60
     Brahman
    -0.60
    POSITIVE LOGITS
     Which
    0.74
     vilket
    0.70
    Which
    0.69
     což
    0.67
     WHICH
    0.64
    which
    0.64
     which
    0.63
     mathvariant
    0.63
     luckily
    0.62
    requireNonNull
    0.60
    Activations Density 0.242%

    No Known Activations