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. 15-GEMMASCOPE-RES-16K
    6. 2000
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.66
     незавершена
    -0.65
    GraphicsUnit
    -0.63
     ContentValues
    -0.61
     bağlantılar
    -0.61
    )_/¯
    -0.57
    alable
    -0.57
    andidates
    -0.56
    monk
    -0.55
    scre
    -0.55
    POSITIVE LOGITS
     flattered
    0.98
     flattering
    0.78
     humbling
    0.72
     recognition
    0.71
    Appreciate
    0.69
     honored
    0.67
     appreciative
    0.65
     honoured
    0.64
     compliment
    0.64
     awards
    0.64
    Activations Density 0.152%

    No Known Activations