© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12773
    Prev
    Next
    INDEX
    Explanations

    elements related to magazines, especially those targeting specific audiences or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.44
     NSF
    -0.39
     للمعارف
    -0.38
    GIVEREF
    -0.38
    Referencer
    -0.35
     ElementRef
    -0.35
    tyler
    -0.34
    工程
    -0.34
     Genu
    -0.34
     LORD
    -0.33
    POSITIVE LOGITS
     magazine
    1.08
     magazines
    0.97
    magazine
    0.91
     Magazine
    0.89
    Magazine
    0.78
     MAGAZINE
    0.77
     revista
    0.74
    杂志
    0.69
     Magazines
    0.69
    MAGAZINE
    0.68
    Activations Density 0.165%

    No Known Activations