Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 5147
    Prev
    Next
    INDEX
    Explanations

    references to activities or events occurring on Fridays or weekends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mew
    -0.91
    Datuak
    -0.88
    Mew
    -0.76
     Trent
    -0.68
     Mire
    -0.67
    ثيق
    -0.67
    addSubview
    -0.67
    deepEqual
    -0.66
    orsche
    -0.66
     Jody
    -0.65
    POSITIVE LOGITS
     Friday
    1.17
    FRIDAY
    1.17
     FRIDAY
    1.16
     saturday
    1.14
    SATURDAY
    1.14
     friday
    1.14
     SATURDAY
    1.13
     Saturday
    1.13
    Friday
    1.11
    Viernes
    1.11
    Activations Density 0.058%

    No Known Activations