© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4592
    Prev
    Next
    INDEX
    Explanations

    temporal phrases related to events and durations

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

    Immediately after a specific event

    np_acts-logits-general · gemini-2.0-flash

    after a duration or event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     macam
    -0.29
     litt
    -0.28
     limitée
    -0.26
     egész
    -0.24
     CORRESPOND
    -0.24
     players
    -0.24
    多年
    -0.23
     spécialistes
    -0.23
    modelBuilder
    -0.23
     빠
    -0.23
    POSITIVE LOGITS
     nakalista
    0.79
    IntoConstraints
    0.79
    ValueStyle
    0.78
    VersionUID
    0.72
    posedge
    0.71
     arşivlendi
    0.69
    scriptcase
    0.67
    
    0.66
     disambiguazione
    0.65
    principalColumn
    0.62
    Activations Density 0.322%

    No Known Activations