© 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. 9480
    Prev
    Next
    INDEX
    Explanations

    financial and economic implications, particularly regarding budgets and resource management

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

    Word followed by a modal verb

    np_acts-logits-general · gemini-2.0-flash

    future potential or likelihood

    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
     pinulongan
    -0.61
     होते
    -0.60
    ūd
    -0.57
     ***!
    -0.55
     होता
    -0.53
     vengono
    -0.53
    IsMutable
    -0.52
    :✨
    -0.50
     হয়
    -0.47
     beginnetje
    -0.47
    POSITIVE LOGITS
     threatens
    0.93
     promises
    0.91
     could
    0.77
     needs
    0.77
     presents
    0.73
     remains
    0.73
     promise
    0.72
     appears
    0.72
     will
    0.72
    promises
    0.71
    Activations Density 0.440%

    No Known Activations