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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 6800
    Prev
    Next
    INDEX
    Explanations

    negations and contractions of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.64
     Chwiliwch
    -0.51
    存于互联网档案馆
    -0.50
    EIF
    -0.50
     Pij
    -0.49
     ujednoznacz
    -0.48
    URLException
    -0.48
    ,$_
    -0.46
    saurus
    -0.45
    jší
    -0.44
    POSITIVE LOGITS
    wouldn
    0.90
     didn
    0.88
     doesn
    0.88
     wasn
    0.87
     wouldn
    0.85
     aren
    0.85
    doesn
    0.84
    didn
    0.82
     weren
    0.82
    Wouldn
    0.82
    Activations Density 0.099%

    No Known Activations