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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14411
    Prev
    Next
    INDEX
    Explanations

    phrases reflecting unexpected outcomes or realizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remb
    -0.46
    postsleuth
    -0.46
    IVEREF
    -0.46
     tetrach
    -0.45
    出版年
    -0.45
     fusca
    -0.42
    ismet
    -0.42
    Personendaten
    -0.41
    uvre
    -0.41
    uvres
    -0.41
    POSITIVE LOGITS
     unexpected
    0.74
    まさか
    0.71
     unforeseen
    0.67
     surprise
    0.63
     Unexpected
    0.63
     unexpectedly
    0.61
     surprises
    0.61
    Unexpected
    0.59
     expected
    0.58
     expecting
    0.58
    Activations Density 0.255%

    No Known Activations