© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9982
    Prev
    Next
    INDEX
    Explanations

    references to rules, responsibilities, and care related to relationships or contracts

    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
    borderFill
    -0.44
    bootstrapcdn
    -0.43
    HtmlAttribute
    -0.41
    istungs
    -0.40
     définiti
    -0.39
     الجمع
    -0.38
    tactez
    -0.38
    ffled
    -0.37
     голо
    -0.37
     refunded
    -0.36
    POSITIVE LOGITS
     care
    1.02
     cuidados
    1.01
     maintenance
    0.97
     cuidado
    0.96
    保养
    0.90
     merawat
    0.89
     cuidar
    0.88
     cuid
    0.88
    maintenance
    0.86
     cuida
    0.85
    Activations Density 0.252%

    No Known Activations