© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3693
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest change or improvement in various contexts

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

    "Even," "lot," or "much" followed by a comparative

    np_acts-logits-general · gemini-2.0-flash

    even more / much more / lot more

    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
     ſtate
    -0.83
    ſelf
    -0.78
     eſt
    -0.74
     purpoſe
    -0.74
     deſt
    -0.73
     myſelf
    -0.71
     itſelf
    -0.71
     ſmall
    -0.70
     houſe
    -0.69
     ſche
    -0.69
    POSITIVE LOGITS
     friend
    0.68
     nas
    0.65
     dir
    0.64
     pla
    0.61
     classi
    0.61
     guil
    0.61
     sc
    0.61
    ChromeDriver
    0.61
     mes
    0.60
     lus
    0.59
    Activations Density 0.193%

    No Known Activations