© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5315
    Prev
    Next
    INDEX
    Explanations

    instances of the word "switch" and its variations, indicating a focus on changing states or transitions

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

    a change or transition

    np_acts-logits-general · gemini-2.0-flash

    switching states or allegiances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     dieux
    -0.48
    nhung
    -0.48
     speciale
    -0.48
     tasche
    -0.47
    alisasi
    -0.46
    kosh
    -0.45
     corriger
    -0.44
     OTHERWISE
    -0.43
    oblotting
    -0.43
    ReusableCell
    -0.43
    POSITIVE LOGITS
     gears
    1.15
    gears
    0.90
     roles
    0.87
     sides
    0.86
     allegiance
    0.81
     lanes
    0.80
    gear
    0.80
     positions
    0.78
     modes
    0.78
     gear
    0.77
    Activations Density 0.195%

    No Known Activations