© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13332
    Prev
    Next
    INDEX
    Explanations

    terms related to immediacy and promptness

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

    temporal proximity

    np_acts-logits-general · gemini-2.0-flash

    immediately before or after

    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
     finally
    -1.04
    Finally
    -0.94
    finally
    -0.94
     Finally
    -0.91
     eventually
    -0.90
    eventually
    -0.87
     Finalmente
    -0.85
     ultimately
    -0.83
    Finalmente
    -0.81
     slowly
    -0.81
    POSITIVE LOGITS
     thereafter
    1.03
    aneous
    0.84
     recognizable
    0.77
     recognisable
    0.75
     afterwards
    0.71
     chóng
    0.69
    aneously
    0.68
     Thereafter
    0.68
     regretted
    0.67
     gratification
    0.66
    Activations Density 0.147%

    No Known Activations