© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 12063
    Prev
    Next
    INDEX
    Explanations

    terms related to "night" and "nightlife."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.55
    XmlAccessorType
    -0.50
     pomeriggio
    -0.49
    rungsseite
    -0.48
    webtoken
    -0.46
    下午
    -0.44
    oneofs
    -0.44
    PropertyChanging
    -0.43
     afternoon
    -0.42
    SBATCH
    -0.42
    POSITIVE LOGITS
    ingale
    0.72
    Night
    0.52
     Night
    0.50
    fall
    0.49
     shift
    0.48
     sky
    0.48
    gown
    0.46
    ly
    0.46
    DropTable
    0.44
     Shift
    0.44
    Activations Density 0.066%

    No Known Activations