© 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-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1999
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols commonly used in equations and formulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
     ſche
    -1.00
     houſe
    -0.93
     autorytatywna
    -0.91
    AddTagHelper
    -0.91
     ब्रेकडाउन
    -0.90
     ſch
    -0.88
     pinulongan
    -0.86
    expandindo
    -0.86
     faſt
    -0.82
    GEBURTSDATUM
    -0.82
    POSITIVE LOGITS
     to
    0.49
     or
    0.47
     and
    0.47
    ,
    0.44
     is
    0.40
    (&:
    0.38
     are
    0.38
    ó
    0.36
     in
    0.36
    iz
    0.36
    Activations Density 1.505%

    No Known Activations