© 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. 15-GEMMASCOPE-RES-16K
    6. 5649
    Prev
    Next
    INDEX
    Explanations

    technical definitions and configuration parameters related to computing systems and protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GZIP
    -0.63
    kkit
    -0.50
     sk
    -0.50
    orrho
    -0.49
    trecht
    -0.47
     ca
    -0.47
     meta
    -0.46
     an
    -0.46
    anInt
    -0.46
     la
    -0.46
    POSITIVE LOGITS
     zijne
    0.81
     pleaſure
    0.81
     الرياضيه
    0.79
     ProtoMessage
    0.78
    sizeCache
    0.77
     CreateTagHelper
    0.76
     twain
    0.76
     ſhe
    0.76
     Shakspeare
    0.76
     uſed
    0.75
    Activations Density 0.751%

    No Known Activations