© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 323
    Prev
    Next
    INDEX
    Explanations

    the word "today" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Today" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    today's events and times of day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Дереккөздер
    -0.90
    __':
    -0.89
    __":
    -0.87
    ]').
    -0.83
    ]--;
    -0.79
     kasarigan
    -0.78
    __":
    -0.77
    ]')
    -0.76
    "]').
    -0.73
    queryInterface
    -0.73
    POSITIVE LOGITS
     pomeriggio
    1.00
     morning
    0.81
     afternoon
    0.70
     Morgen
    0.70
     Abend
    0.70
     Nachmittag
    0.65
     evening
    0.61
    날
    0.60
     morn
    0.60
    evening
    0.57
    Activations Density 0.035%

    No Known Activations