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. 25-GEMMASCOPE-RES-16K
    6. 12474
    Prev
    Next
    INDEX
    Explanations

    terms related to propensity scores and their applications in statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proposal
    -0.68
     propuesta
    -0.64
     proposta
    -0.62
     propuestas
    -0.62
     process
    -0.61
     proposto
    -0.61
     ProtoMessage
    -0.61
    Practical
    -0.61
     proposed
    -0.60
    }{*}{}
    -0.60
    POSITIVE LOGITS
    Rüyada
    0.57
     nouns
    0.55
     intellectuelle
    0.55
     Punt
    0.54
    bably
    0.54
    ensity
    0.52
     Pik
    0.51
    ffes
    0.49
    ESSOR
    0.48
    ressional
    0.47
    Activations Density 0.420%

    No Known Activations