© 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. 13-GEMMASCOPE-RES-16K
    11. 1847
    Prev
    Next
    INDEX
    Explanations

    phrases related to mental and emotional control or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nsf
    -0.50
     sepen
    -0.46
    krankungen
    -0.45
    accident
    -0.43
    manjaro
    -0.43
    mbggenerated
    -0.43
    ongo
    -0.42
    Meno
    -0.42
     Care
    -0.42
     care
    -0.42
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.95
     instead
    0.83
    Instead
    0.82
     Instead
    0.79
    instead
    0.76
    tdessen
    0.72
     rather
    0.68
     Rather
    0.66
    Rather
    0.64
     lieber
    0.62
    Activations Density 0.337%

    No Known Activations