© 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. 27-GEMMASCOPE-RES-16K
    11. 9840
    Prev
    Next
    INDEX
    Explanations

    instances of the word "instead."

    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
    ArgsConstructor
    -0.56
     cú
    -0.44
    MessageOf
    -0.43
    ❋
    -0.42
    UIC
    -0.41
    unknownFields
    -0.40
     demais
    -0.39
    ьаж
    -0.38
    UW
    -0.38
    outWeight
    -0.38
    POSITIVE LOGITS
     betweenstory
    0.64
    Instead
    0.54
    Rather
    0.51
    instead
    0.48
     Instead
    0.48
     mergeFrom
    0.47
     than
    0.46
     opting
    0.45
     instead
    0.44
     Rather
    0.44
    Activations Density 0.117%

    No Known Activations