Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10995
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and requirements related to notice periods and legal language

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

    preceding "notice" or variations of it

    np_acts-logits-general · gemini-2.0-flash

    prior notice or notification

    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
    </thead>
    -0.65
    URLException
    -0.51
    Биография
    -0.51
    CardContent
    -0.49
    GenerationType
    -0.47
    initializeApp
    -0.43
     rispond
    -0.43
    ylim
    -0.43
    UnitTesting
    -0.43
     án
    -0.42
    POSITIVE LOGITS
     notice
    2.51
    notice
    2.09
     Notice
    2.08
     notification
    2.03
    Notice
    1.95
     notices
    1.89
     NOTICE
    1.81
     Notices
    1.70
     Notification
    1.66
    NOTICE
    1.64
    Activations Density 0.584%

    No Known Activations