© 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. 1607
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms related to engineering processes and fluid dynamics

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

    Verbs indicating a change or reaction

    np_acts-logits-general · gemini-2.0-flash

    physical or chemical processes

    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
    AsUp
    -0.65
    enumi
    -0.61
    ględ
    -0.58
     getItemCount
    -0.52
     Hers
    -0.51
     Chwiliwch
    -0.51
    HOY
    -0.51
    었습니다
    -0.50
    ্ন
    -0.50
    تفصیلات
    -0.50
    POSITIVE LOGITS
     causing
    0.86
     whereupon
    0.79
     producing
    0.77
    causing
    0.73
     infolge
    0.69
     resulting
    0.69
     forming
    0.69
     thereby
    0.68
     provocando
    0.68
     due
    0.66
    Activations Density 1.492%

    No Known Activations