© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12630
    Prev
    Next
    INDEX
    Explanations

    events and activities involving social interactions and gatherings

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

    Action or state followed by a time-related preposition

    np_acts-logits-general · gemini-2.0-flash

    times of day and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.46
     samenwerking
    -0.44
     élev
    -0.42
     advantages
    -0.41
     kontinu
    -0.41
     voordelen
    -0.41
    vän
    -0.40
     Gründung
    -0.40
     annually
    -0.40
    Advantages
    -0.40
    POSITIVE LOGITS
     lunch
    0.56
     afternoon
    0.53
    afternoon
    0.50
     errands
    0.50
     dinner
    0.48
     tonight
    0.47
    principalColumn
    0.46
     evening
    0.45
     hour
    0.45
     supper
    0.45
    Activations Density 0.311%

    No Known Activations