© 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. 41-GEMMASCOPE-RES-16K
    11. 7160
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.48
    expandindo
    -0.45
     resourceCulture
    -0.38
     typelib
    -0.38
    FER
    -0.38
    NameInMap
    -0.37
     RouterModule
    -0.36
     FU
    -0.35
    IFO
    -0.35
    ClientRect
    -0.35
    POSITIVE LOGITS
     f
    2.95
    f
    2.56
    ｆ
    1.41
    𝑓
    1.16
     ƒ
    1.05
    フ
    0.96
    ф
    0.90
    fD
    0.88
     ف
    0.88
     ф
    0.88
    Activations Density 1.555%

    No Known Activations