© 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. 27-GEMMASCOPE-RES-16K
    6. 10474
    Prev
    Next
    INDEX
    Explanations

    specific references to brands, styles, or types of products and their attributes in a technology or cultural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plufieurs
    -0.47
     Monfieur
    -0.37
     onely
    -0.36
     myſelf
    -0.36
     Sustainability
    -0.35
     whoſe
    -0.35
     privaten
    -0.35
     späteren
    -0.35
     tertulis
    -0.34
     Conſ
    -0.34
    POSITIVE LOGITS
     style
    1.01
    style
    0.86
    esque
    0.82
    like
    0.82
     STYLE
    0.70
    expandindo
    0.70
     vibes
    0.69
     mentality
    0.68
    LIKE
    0.68
     estilo
    0.66
    Activations Density 0.623%

    No Known Activations