© 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 EvalsExportsinterp-engineNEWAPI 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. 12316
    Prev
    Next
    INDEX
    Explanations

    elements related to daily routines and personal interactions

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

    departures or leaving

    np_acts-logits-general · gemini-2.0-flash

    leaving start

    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
     MainAxisSize
    -0.44
     position
    -0.43
     EconPapers
    -0.42
    jda
    -0.42
    ($__
    -0.40
     ostavi
    -0.39
    usercontent
    -0.39
     Vikipedi
    -0.39
     falls
    -0.39
    demik
    -0.39
    POSITIVE LOGITS
     departure
    1.15
     departing
    1.11
     Departure
    1.02
    departure
    1.02
    Departure
    0.95
     departures
    0.95
     depart
    0.94
     outbound
    0.91
     départ
    0.90
     outgoing
    0.90
    Activations Density 0.429%

    No Known Activations