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. 12731
    Prev
    Next
    INDEX
    Explanations

    themes of trauma and transformation in characters

    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
     Cæsar
    -0.72
    omeness
    -0.71
     <>",
    -0.69
     myſelf
    -0.69
    存于互联网档案馆
    -0.68
     שוליים
    -0.68
     scraper
    -0.67
     groupName
    -0.67
     Rambo
    -0.67
     Cleopatra
    -0.67
    POSITIVE LOGITS
    protoimpl
    0.71
     ability
    0.54
     living
    0.52
    living
    0.47
     trans
    0.47
    complexType
    0.47
    fitriones
    0.46
    Pranala
    0.46
     mode
    0.46
     jalan
    0.45
    Activations Density 0.499%

    No Known Activations