© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5773
    Prev
    Next
    INDEX
    Explanations

    phrases related to delays and prolonged situations, particularly in a legislative or bureaucratic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fxml
    -0.54
    ITAT
    -0.50
    olit
    -0.44
     Po
    -0.43
     na
    -0.40
    isting
    -0.39
    <bos>
    -0.39
    FolderPath
    -0.38
    BorderWidth
    -0.38
     recensement
    -0.38
    POSITIVE LOGITS
     delays
    1.43
     delay
    1.40
     Delays
    1.39
     delaying
    1.37
     Delay
    1.30
     delayed
    1.26
     DELAY
    1.24
     Delayed
    1.16
    Delay
    1.15
    delay
    1.13
    Activations Density 0.306%

    No Known Activations