© 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. 33-GEMMASCOPE-RES-16K
    11. 7946
    Prev
    Next
    INDEX
    Explanations

    mentions of diverse global communities and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.66
    DockStyle
    -0.61
    addContainerGap
    -0.57
    InSection
    -0.57
    Overall
    -0.56
     препратки
    -0.55
     Overall
    -0.54
     насељу
    -0.54
    EDEFAULT
    -0.53
    Worldwide
    -0.51
    POSITIVE LOGITS
    OGND
    0.49
     corners
    0.47
     around
    0.46
     far
    0.39
     ympä
    0.38
     locations
    0.38
    corners
    0.35
     dört
    0.34
     nearly
    0.33
     virtually
    0.32
    Activations Density 0.165%

    No Known Activations