© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9970
    Prev
    Next
    INDEX
    Explanations

    annual events and gatherings related to sports and community activities

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

    time, dates or yearly events

    np_acts-logits-general · gemini-2.0-flash

    annual and yearly occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.53
    StoryboardSegue
    -0.49
    .*")]
    -0.47
    :✨
    -0.45
    Autoritní
    -0.42
    nonatomic
    -0.41
    droje
    -0.39
     Autorisations
    -0.37
    ParallelGroup
    -0.36
     Signalez
    -0.36
    POSITIVE LOGITS
     yearly
    1.91
     annually
    1.88
     annual
    1.86
    annual
    1.66
    毎年
    1.62
     anual
    1.56
    每年
    1.53
    yearly
    1.51
    Annual
    1.49
     Annual
    1.45
    Activations Density 0.456%

    No Known Activations