© 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. 14640
    Prev
    Next
    INDEX
    Explanations

    specific scientific or technical terminologies and acronyms, particularly in the context of Gaussian random fields and advanced materials

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

    Abbreviations/acronyms followed by a capital letter

    np_acts-logits-general · gemini-2.0-flash

    initialisms followed by common suffixes

    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
     CCC
    -0.76
     PPA
    -0.72
     HH
    -0.67
     KK
    -0.66
     PPD
    -0.66
     BCC
    -0.66
     BBB
    -0.66
     MMM
    -0.65
     CCL
    -0.64
     BBM
    -0.64
    POSITIVE LOGITS
     désolés
    0.60
    TagMode
    0.58
    Xna
    0.54
    NewGuid
    0.54
     HasFactory
    0.53
     BoxFit
    0.52
    dhury
    0.49
     dAtA
    0.48
    Batis
    0.48
    amling
    0.48
    Activations Density 0.446%

    No Known Activations