© 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. 7298
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to compounds and chemical processes

    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
     GenerationType
    -0.38
    IsMutable
    -0.36
    IndentedString
    -0.35
    dafx
    -0.34
    AnimationsModule
    -0.34
     Scra
    -0.34
     Sasha
    -0.33
    帖最后由
    -0.32
     SAC
    -0.32
    ysacchar
    -0.32
    POSITIVE LOGITS
     Si
    1.88
    Si
    1.77
     si
    1.74
    si
    1.66
     SI
    1.65
    SI
    1.55
     Sib
    1.48
     silic
    1.47
     Си
    1.46
     Sí
    1.45
    Activations Density 3.577%

    No Known Activations