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. 1-GEMMASCOPE-RES-16K
    6. 4630
    Prev
    Next
    INDEX
    Explanations

    references to mortality or death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    archiviato
    -0.67
    urgis
    -0.63
     >=",
    -0.55
    ьаж
    -0.55
    WriteTagHelper
    -0.54
     ویکی‌پدی
    -0.53
    indd
    -0.53
    乓
    -0.52
     jug
    -0.52
    titial
    -0.52
    POSITIVE LOGITS
     flows
    0.87
     Flows
    0.79
     dying
    0.78
     Dying
    0.77
    Flows
    0.69
    ViewImports
    0.66
    flows
    0.66
    Dying
    0.66
    relate
    0.66
     seuls
    0.64
    Activations Density 0.138%

    No Known Activations