© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15316
    Prev
    Next
    INDEX
    Explanations

    elements related to date and time handling in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omni
    -0.50
     MonoBehaviour
    -0.43
     Hey
    -0.43
     inher
    -0.40
    VersionUID
    -0.40
    ConstraintMaker
    -0.40
     Gabri
    -0.39
     EconPapers
    -0.39
    hom
    -0.39
    csp
    -0.39
    POSITIVE LOGITS
     date
    2.83
     Date
    2.59
    Date
    2.56
    date
    2.45
     DATE
    2.34
    DATE
    2.23
     dates
    2.22
     Dates
    2.11
    dates
    1.95
    Dates
    1.90
    Activations Density 0.063%

    No Known Activations