© 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. 7990
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and terms in the context of equations and scientific notation

    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
     ret
    -0.38
    .
    -0.38
     види
    -0.38
     „
    -0.37
    rebbe
    -0.37
     “
    -0.37
    mt
    -0.36
     seri
    -0.36
     ”
    -0.36
    руса
    -0.36
    POSITIVE LOGITS
    StructEnd
    0.84
     كومونز
    0.84
     дописавши
    0.83
     فريبيس
    0.82
     оригіналу
    0.81
    GEBURTSDATUM
    0.79
     Efq
    0.79
    UnknownFields
    0.78
     itſelf
    0.78
     pleaſure
    0.77
    Activations Density 1.264%

    No Known Activations