© 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. 3-GEMMASCOPE-RES-16K
    11. 5498
    Prev
    Next
    INDEX
    Explanations

    structured mathematical expressions and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \\
    -0.55
    \\
    -0.50
    ToProps
    -0.41
     pri
    -0.40
     &
    -0.39
     vie
    -0.39
     \&
    -0.38
     dey
    -0.37
     tri
    -0.37
     su
    -0.35
    POSITIVE LOGITS
     HasFactory
    0.66
     ProtoMessage
    0.57
     OFDb
    0.56
     виправивши
    0.54
    abestanden
    0.54
     extranjera
    0.54
    ļi
    0.53
    liceerd
    0.52
     GenerationType
    0.52
     سكانية
    0.51
    Activations Density 0.342%

    No Known Activations